© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 74479
    Prev
    Next
    INDEX
    Explanations

    Technical documentation

    np_max-act-logits · 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
    ✨:
    -0.53
    raise
    -0.51
     raised
    -0.50
     raise
    -0.49
    raised
    -0.49
    ISES
    -0.47
    ConstraintMaker
    -0.46
    getStatusCode
    -0.46
     مشين
    -0.46
    -------
    -0.45
    POSITIVE LOGITS
    AutoScaleMode
    0.57
    GrantedAuthority
    0.54
     EconPapers
    0.53
    umą
    0.53
    gbarkeit
    0.52
     trơn
    0.49
     Perio
    0.48
    Tikang
    0.48
     Berta
    0.48
    ScopeManager
    0.48
    Activations Density 0.000%

    No Known Activations