© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 43828
    Prev
    Next
    INDEX
    Explanations

    Code special characters

    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
     licensee
    -0.91
     licensees
    -0.84
     Efq
    -0.81
     pleaſure
    -0.68
    ethene
    -0.66
     negroes
    -0.66
     niedersachsen
    -0.64
    asmuch
    -0.64
    OfMonth
    -0.63
     grecque
    -0.61
    POSITIVE LOGITS
    PreferredItem
    0.71
     الدولى
    0.56
     part
    0.52
    MigrationBuilder
    0.52
     am
    0.52
     فريبيس
    0.49
    ступить
    0.48
     dan
    0.48
    AnchorStyles
    0.48
     AN
    0.47
    Activations Density 0.229%

    No Known Activations