Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 73849
    Prev
    Next
    INDEX
    Explanations

    code, technical writing

    np_max-act-logits · 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
     REACTOR
    -0.57
    ppins
    -0.57
    PRNewswire
    -0.57
     igång
    -0.57
     fú
    -0.56
    zyści
    -0.54
     אביב
    -0.54
    RAE
    -0.54
     pamamagitan
    -0.54
    ectoria
    -0.53
    POSITIVE LOGITS
    jspx
    0.58
    IndentedString
    0.55
    ########.
    0.53
    contentLoaded
    0.50
    ודם
    0.49
    AutoScaleMode
    0.47
    VIR
    0.45
    elemField
    0.45
     estimés
    0.45
    DropColumn
    0.44
    Activations Density 0.006%

    No Known Activations