© 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. 0-CLT-HP
    7. 92073
    Prev
    Next
    INDEX
    Explanations

    technical/scientific topics

    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
     zöld
    -0.49
     télécommande
    -0.45
    maker
    -0.45
    arXiv
    -0.44
    createCanvas
    -0.44
    UnifiedTopology
    -0.44
     témo
    -0.44
     stål
    -0.44
     stratég
    -0.43
    MILLIS
    -0.43
    POSITIVE LOGITS
    <bos>
    0.71
    सन्दर्भ
    0.63
    </thead>
    0.60
    ⓧ
    0.60
     sth
    0.59
    PostExecute
    0.58
     initComponents
    0.57
     linkovi
    0.57
     postIndex
    0.56
     uska
    0.56
    Activations Density 1.728%

    No Known Activations