© 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. 5-CLT-HP
    7. 95146
    Prev
    Next
    INDEX
    Explanations

    technical descriptions/specifications

    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
     liberté
    -0.45
     puisi
    -0.37
    quire
    -0.36
     kondisi
    -0.36
     you
    -0.36
     номер
    -0.35
     Vorteil
    -0.34
    mediaType
    -0.34
     varsa
    -0.34
     consente
    -0.34
    POSITIVE LOGITS
    mybatisplus
    1.02
    contentLoaded
    0.91
     nakalista
    0.90
    ViewFeatures
    0.85
    Rüyada
    0.84
    UnsafeEnabled
    0.84
     ostavi
    0.82
    AsUp
    0.80
    parsedMessage
    0.79
    UnknownFields
    0.79
    Activations Density 0.000%

    No Known Activations