© 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. 15137
    Prev
    Next
    INDEX
    Explanations

    ll

    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
    ll
    -0.65
    makeConstraints
    -0.63
    RuleContext
    -0.56
    JpaRepository
    -0.54
    :✨
    -0.52
    DropTable
    -0.52
     tarvit
    -0.52
    ResumeLayout
    -0.51
    SuccessListener
    -0.50
     romántico
    -0.50
    POSITIVE LOGITS
    Aiheesta
    0.63
    PreferredItem
    0.62
    حياتها
    0.55
    ----</
    0.54
    istic
    0.50
    wch
    0.50
    GOTREF
    0.49
     OP
    0.48
    vss
    0.47
     Analysis
    0.46
    Activations Density 0.030%

    No Known Activations