© 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. 2-RES-MATRYOSHKA-DC
    7. 3858
    Prev
    Next
    INDEX
    Explanations

    instructions or guidance

    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
    ⓘ
    -0.69
     Find
    -0.63
     Мексичка
    -0.61
    ValueStyle
    -0.60
    +:+
    -0.59
    AutoScaleMode
    -0.58
    ート
    -0.57
    CreateMap
    -0.57
    antino
    -0.56
    HideFlags
    -0.56
    POSITIVE LOGITS
     let
    2.34
     letting
    1.88
     lets
    1.88
     LET
    1.62
    let
    1.58
     Letting
    1.56
    letting
    1.55
    Letting
    1.45
    Let
    1.38
     Let
    1.36
    Activations Density 0.075%

    No Known Activations