© 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
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 97088
    Prev
    Next
    INDEX
    Explanations

    of

    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
    "):
    -0.86
    XMLSchema
    -0.82
    DockStyle
    -0.82
    }{*}{}
    -0.79
    __':
    -0.78
    __":
    -0.76
    SequentialGroup
    -0.75
    AnchorStyles
    -0.75
    ConstraintMaker
    -0.74
    )";
    -0.73
    POSITIVE LOGITS
     sonre
    0.41
     sahiptir
    0.38
     cread
    0.38
     completos
    0.38
     жов
    0.34
     termasuk
    0.34
     colazione
    0.34
    <bos>
    0.33
     път
    0.33
     caer
    0.33
    Activations Density 0.100%

    No Known Activations