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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 4516
    Prev
    Next
    INDEX
    Explanations

    Battista

    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
    Personensuche
    -0.94
    mybatisplus
    -0.91
    SequentialGroup
    -0.88
    GraphicsUnit
    -0.78
    parsedMessage
    -0.74
     jsPsych
    -0.71
    WireFormatLite
    -0.71
     iprot
    -0.71
    ftagPool
    -0.69
    tagHelperRunner
    -0.66
    POSITIVE LOGITS
    ἶ
    0.47
     zve
    0.43
    Articles
    0.42
    aS
    0.42
    ais
    0.42
    DECREF
    0.40
    zards
    0.40
    ahs
    0.39
    ACTERS
    0.39
    нец
    0.39
    Activations Density 0.004%

    No Known Activations