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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 0-RES-JB
    6. 404
    Prev
    Next
    INDEX
    Explanations

    mentions or descriptions of 'mandolin' - a musical instrument

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    316
    +0.11
    0.3%
    1708
    +0.10
    0.3%
    795
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.11
    0.03
    1120
    +0.10
    0.03
    1343
    +0.10
    0.03
    Negative Logits
     lørdag
    -0.90
     fredag
    -0.87
     næste
    -0.84
     fået
    -0.82
     søndag
    -0.80
     onsdag
    -0.80
     nogen
    -0.77
     rigtig
    -0.77
     køb
    -0.74
     endnu
    -0.73
    POSITIVE LOGITS
     Mand
    2.74
     mand
    2.69
    Mand
    2.45
    mand
    2.31
     MAND
    1.86
    MAND
    1.73
     manda
    1.59
     mandar
    1.41
    mands
    1.37
    manda
    1.18
    Activations Density 0.255%

    No Known Activations