© 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. 94448
    Prev
    Next
    INDEX
    Explanations

    saw

    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
     Majefty
    -0.75
     Anſ
    -0.75
     reaſon
    -0.69
     Reſ
    -0.68
     Houſe
    -0.68
     greateſt
    -0.68
     houſe
    -0.67
     faſt
    -0.66
     doubtnut
    -0.66
     neceff
    -0.65
    POSITIVE LOGITS
     me
    0.97
     us
    0.79
     it
    0.75
     them
    0.71
     him
    0.69
     a
    0.63
     some
    0.63
     her
    0.62
    Personensuche
    0.60
     the
    0.59
    Activations Density 0.051%

    No Known Activations