© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 41702
    Prev
    Next
    INDEX
    Explanations

    SF (San Francisco/Science Fiction)

    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
     heavier
    -0.69
    Personendaten
    -0.65
    AccessFile
    -0.62
    adaptiveStyles
    -0.60
     tartalomajánló
    -0.60
     dand
    -0.60
     autorytatywna
    -0.58
     Monfieur
    -0.56
     Prensa
    -0.54
    soever
    -0.54
    POSITIVE LOGITS
    HtmlAttribute
    0.65
    InjectAttribute
    0.59
    extendable
    0.56
    SerializedSize
    0.55
     Bet
    0.52
     externes
    0.52
    GREATER
    0.51
    BIOGRAPHY
    0.51
    ("$.
    0.50
    setVerticalGroup
    0.48
    Activations Density 0.076%

    No Known Activations