© 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. 0-CLT-HP
    7. 95256
    Prev
    Next
    INDEX
    Explanations

    best

    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
     preferred
    -0.61
    таратура
    -0.60
     the
    -0.57
     createStore
    -0.56
    UnitTesting
    -0.55
     prefer
    -0.55
    preferred
    -0.53
    batore
    -0.53
     an
    -0.52
     it
    -0.50
    POSITIVE LOGITS
     cauſe
    0.74
     reaſon
    0.74
     purpoſe
    0.73
     Houſe
    0.72
     Majefty
    0.71
     houſe
    0.68
     myſelf
    0.68
     ſtate
    0.68
     Monfieur
    0.67
     Chriſt
    0.66
    Activations Density 0.086%

    No Known Activations