© 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. 5535
    Prev
    Next
    INDEX
    Explanations

    fool

    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
     houſe
    -0.71
     ainfi
    -0.69
     whoſe
    -0.69
     greateſt
    -0.68
     Efq
    -0.66
     myſelf
    -0.66
     faſt
    -0.64
     Monfieur
    -0.63
     becauſe
    -0.62
     perſon
    -0.62
    POSITIVE LOGITS
    HideFlags
    0.54
    verifyException
    0.52
    tig
    0.52
    ngdoc
    0.49
    MergeFrom
    0.48
     excellent
    0.48
    avadoc
    0.47
     Ce
    0.46
    Péri
    0.46
     ce
    0.46
    Activations Density 0.002%

    No Known Activations