© 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. 5-CLT-HP
    7. 91899
    Prev
    Next
    INDEX
    Explanations

    to be/have

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ագրություններ
    -0.61
    脚注の使い方
    -0.52
    קישורים
    -0.50
    Portale
    -0.49
     henvisninger
    -0.48
     متعلقه
    -0.48
    허
    -0.46
     nakalista
    -0.46
    הערות
    -0.45
    новништво
    -0.45
    POSITIVE LOGITS
    ]--;
    0.70
     then
    0.63
    popd
    0.56
     mères
    0.56
     oiseaux
    0.56
     Jefus
    0.54
     rêver
    0.54
    ,:);
    0.54
     pauvres
    0.53
     chiens
    0.52
    Activations Density 0.002%

    No Known Activations