© 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. 4-CLT-HP
    7. 905
    Prev
    Next
    INDEX
    Explanations

    weather

    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
    AppMethodBeat
    -0.68
     weather
    -0.56
     biv
    -0.47
     Chwiliwch
    -0.46
     Weather
    -0.44
     ged
    -0.42
    __':
    -0.42
     Dich
    -0.42
     Spend
    -0.41
    PhysRevLett
    -0.41
    POSITIVE LOGITS
    tvguidetime
    0.71
     autorytatywna
    0.71
    principalColumn
    0.69
     ModelExpression
    0.68
     disponibilités
    0.65
    SourceChecksum
    0.59
     المعرف
    0.57
     CreateTagHelper
    0.57
    tometer
    0.57
     continúas
    0.57
    Activations Density 0.004%

    No Known Activations