© 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. 42695
    Prev
    Next
    INDEX
    Explanations

    effect

    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
     effect
    -1.52
    effect
    -1.34
     Effect
    -1.13
    Effect
    -0.98
     efecto
    -0.91
     EFFECT
    -0.88
     effet
    -0.84
    effet
    -0.79
     effects
    -0.68
    效应
    -0.66
    POSITIVE LOGITS
     himo
    0.67
    ⓧ
    0.67
    NewUrlParser
    0.65
     виправивши
    0.62
     calendriers
    0.60
    Datuak
    0.60
    رشف
    0.59
     Biôgrafia
    0.59
     HasFactory
    0.58
    +:+
    0.57
    Activations Density 0.027%

    No Known Activations