© 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. 1-CLT-HP
    7. 10389
    Prev
    Next
    INDEX
    Explanations

    lenti

    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
     lick
    -0.42
     Wern
    -0.40
    publique
    -0.39
    xaml
    -0.39
    WriteAttribute
    -0.36
    agramm
    -0.36
     Lick
    -0.35
     Federation
    -0.35
     Überg
    -0.35
    aaral
    -0.35
    POSITIVE LOGITS
     تضيفلها
    0.90
    PyExc
    0.84
    migrationBuilder
    0.81
    expandindo
    0.79
    rungsseite
    0.77
    '}>
    0.75
    ]-'
    0.71
    PathVariable
    0.70
    ']->
    0.68
     FormsModule
    0.67
    Activations Density 0.012%

    No Known Activations