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

    Neuronpedia

    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. 12750
    Prev
    Next
    INDEX
    Explanations

    phrases related to retrospective reflection

    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
    481
    +0.08
    0.2%
    872
    +0.08
    0.2%
    776
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1081
    +0.08
    0.03
    1477
    +0.08
    0.03
    1043
    +0.08
    0.02
    Negative Logits
     affor
    -1.23
     Juf
    -1.20
     encomp
    -1.16
     impra
    -1.14
     increa
    -1.14
     guarante
    -1.11
     excru
    -1.11
     inev
    -1.10
     volunte
    -1.09
     Keny
    -1.08
    POSITIVE LOGITS
     retrospect
    1.10
     hindsight
    1.08
    <bos>
    0.67
     retro
    0.64
     regrets
    0.64
     retrospective
    0.64
     regret
    0.64
     retrospec
    0.60
    retro
    0.59
    hind
    0.58
    Activations Density 0.159%

    No Known Activations