© 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. 93806
    Prev
    Next
    INDEX
    Explanations

    curl

    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
     renewed
    -0.70
     curl
    -0.60
    ised
    -0.58
    ep
    -0.56
     altered
    -0.56
     AssemblyCulture
    -0.53
     GNP
    -0.52
     Aplica
    -0.52
    et
    -0.50
    uoš
    -0.50
    POSITIVE LOGITS
    AnchorStyles
    0.69
    Portale
    0.68
    Décès
    0.63
    bukkit
    0.62
    Rujuakan
    0.58
    DeleteBehavior
    0.57
     beginnetje
    0.57
    PreferredItem
    0.55
    ValueGenerated
    0.55
     мәкалә
    0.55
    Activations Density 0.193%

    No Known Activations