© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 2370
    Prev
    Next
    INDEX
    Explanations

    instances of someone being honest, true to themselves, or afraid to do something

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CloseOperation
    -0.60
    +:+
    -0.56
     ExecuteAsync
    -0.55
    createCanvas
    -0.54
    rrggbb
    -0.54
    ----</
    -0.51
    (!__
    -0.51
     ARGUMENT
    -0.49
    #+#
    -0.48
    ξι
    -0.48
    POSITIVE LOGITS
     disclose
    1.88
     disclosure
    1.88
     disclosing
    1.84
     revealing
    1.77
     disclosed
    1.75
     reveal
    1.72
     exposing
    1.68
     discloses
    1.68
     expose
    1.67
     exposed
    1.64
    Activations Density 0.991%

    No Known Activations