© 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. 5853
    Prev
    Next
    INDEX
    Explanations

    the word indicating that something is clear or self-evident

    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
    principalColumn
    -0.76
     Sump
    -0.70
    endphp
    -0.70
    Accurate
    -0.65
    ✭✭
    -0.64
     IEnumerable
    -0.63
     Allí
    -0.63
    prepareStatement
    -0.63
    χε
    -0.62
    ActionCreators
    -0.61
    POSITIVE LOGITS
     obvious
    2.89
    obvious
    2.72
    Obvious
    2.34
     obviously
    2.08
     obvio
    1.98
    obviously
    1.98
     Obviously
    1.87
    Obviously
    1.83
    VIOUS
    1.65
     evident
    1.64
    Activations Density 0.020%

    No Known Activations