© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 14688
    Prev
    Next
    INDEX
    Explanations

    phrases related to product reviews

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    964
    +0.12
    0.4%
    1150
    +0.11
    0.3%
    674
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    981
    +0.12
    0.06
    651
    +0.11
    0.03
    227
    +0.10
    0.06
    Negative Logits
    ьаж
    -1.09
    Obrigado
    -0.89
    Obrigada
    -0.87
    цездатний
    -0.86
     تانيه
    -0.85
     насељу
    -0.85
    .*")]
    -0.81
    IsContent
    -0.81
    Зноскі
    -0.79
    !*\
    -0.79
    POSITIVE LOGITS
     reluct
    2.75
     encomp
    2.59
     shenan
    2.54
     increa
    2.48
     impra
    2.46
     affor
    2.44
     disagre
    2.43
     depic
    2.41
     guarante
    2.39
     resear
    2.37
    Activations Density 0.396%

    No Known Activations