© 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. 1-CLT-HP
    7. 386
    Prev
    Next
    INDEX
    Explanations

    we

    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
     merak
    -0.64
    +#+
    -0.60
     Reach
    -0.57
    GeneratedCode
    -0.55
    ')")
    -0.54
    PRNewswire
    -0.54
     Ava
    -0.52
    asso
    -0.50
    anover
    -0.49
    AddField
    -0.49
    POSITIVE LOGITS
    fjspx
    0.59
    principalTable
    0.58
    setVerticalGroup
    0.58
    AutoScaleMode
    0.54
     виправивши
    0.54
    basicConfig
    0.52
    IBOutlet
    0.50
    AddHtmlAttribute
    0.50
    migrationBuilder
    0.50
    httphttps
    0.50
    Activations Density 0.008%

    No Known Activations