© 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. 1-RES-MATRYOSHKA-DC
    7. 750
    Prev
    Next
    INDEX
    Explanations

    statements indicating consistency or agreement

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UnusedPrivate
    -0.72
    DebuggerNonUser
    -0.71
    CodeAttribute
    -0.68
    __*/
    -0.67
    TagMode
    -0.63
     avoient
    -0.63
     تضيفلها
    -0.62
    SelectedValue
    -0.57
     FetchType
    -0.57
    ربای
    -0.57
    POSITIVE LOGITS
     consistent
    4.09
    consistent
    3.84
     Consistent
    3.75
    Consistent
    3.67
     consistency
    3.28
     Consistency
    3.13
    Consistency
    3.00
    consistency
    2.91
     inconsistent
    2.86
     consistently
    2.64
    Activations Density 0.626%

    No Known Activations