© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1834
    Prev
    Next
    INDEX
    Explanations

    that

    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
     say
    -0.58
     have
    -0.56
     you
    -0.55
     are
    -0.55
     we
    -0.54
    have
    -0.53
    awaiter
    -0.52
    Are
    -0.52
     ovat
    -0.50
    Lähteet
    -0.50
    POSITIVE LOGITS
     meant
    0.77
     evening
    0.75
     night
    0.75
     was
    0.71
     morning
    0.69
     weekend
    0.69
     afternoon
    0.69
    Diweddarwch
    0.68
     Theſe
    0.68
     userSchema
    0.66
    Activations Density 0.011%

    No Known Activations