© 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. 7136
    Prev
    Next
    INDEX
    Explanations

    questions related to reasons or causes

    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
     reason
    -1.46
     Reason
    -1.34
    Reason
    -1.29
    reason
    -1.27
     reasons
    -1.08
     REASON
    -1.05
     Reasons
    -0.99
    reasons
    -0.92
    Reasons
    -0.89
    REASON
    -0.84
    POSITIVE LOGITS
     why
    1.58
    why
    1.39
     waarom
    1.19
     varför
    1.14
     pourquoi
    1.13
     Зачем
    1.13
    WHY
    1.08
     hvorfor
    1.08
     WHY
    1.07
     warum
    1.07
    Activations Density 0.017%

    No Known Activations