© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 94464
    Prev
    Next
    INDEX
    Explanations

    oward

    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
    ophyta
    -1.27
    oward
    -0.82
     LCCN
    -0.54
     choo
    -0.54
     TQ
    -0.48
    ➋
    -0.47
    LinkId
    -0.47
    UnifiedTopology
    -0.45
    󠁢
    -0.45
    UAWEI
    -0.45
    POSITIVE LOGITS
    WebVitals
    0.65
    webElementXpaths
    0.60
    Referanser
    0.59
    rungsseite
    0.59
    protoimpl
    0.56
     HasFactory
    0.56
     maschile
    0.55
     grève
    0.55
     gynhyrchwyd
    0.54
    es
    0.53
    Activations Density 0.053%

    No Known Activations