© 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. 2100
    Prev
    Next
    INDEX
    Explanations

    Parentheses and asterisks

    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
    vimeo
    -0.77
    iconque
    -0.58
     snuff
    -0.58
     PFS
    -0.57
    xymatrix
    -0.56
     esternos
    -0.55
     AspNetCore
    -0.55
     PPS
    -0.54
     setDescription
    -0.54
     sketch
    -0.54
    POSITIVE LOGITS
     متعلقه
    0.58
     conservé
    0.57
     الفلك
    0.57
     oprot
    0.54
     démocr
    0.53
     religieuses
    0.53
     devons
    0.50
    lizar
    0.50
    VersionUID
    0.49
    rily
    0.49
    Activations Density 0.008%

    No Known Activations