© 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. 94190
    Prev
    Next
    INDEX
    Explanations

    effects

    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
     effects
    -2.88
    effects
    -2.41
     Effects
    -2.38
    Effects
    -2.27
     EFFECTS
    -2.14
     effect
    -1.95
     effets
    -1.92
    effect
    -1.73
     Effect
    -1.70
    Effect
    -1.68
    POSITIVE LOGITS
    entibus
    0.68
     eccell
    0.65
     andato
    0.63
     riuscito
    0.63
     apparaissent
    0.62
     cérami
    0.59
     sogno
    0.59
    rzez
    0.58
     AssemblyCompany
    0.57
    HasForeignKey
    0.57
    Activations Density 1.723%

    No Known Activations