© 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. 45569
    Prev
    Next
    INDEX
    Explanations

    scientific/technical language

    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
    tists
    -0.86
    tist
    -0.82
     تانيه
    -0.60
     endfor
    -0.50
    Volumen
    -0.48
     Crim
    -0.47
    mittent
    -0.46
    ésus
    -0.45
    issors
    -0.45
    OMBIA
    -0.45
    POSITIVE LOGITS
    featureID
    0.63
     <<<<<<<<<<<<<<
    0.62
     cherchés
    0.61
     HasFactory
    0.60
     nakalista
    0.59
    ImageField
    0.59
     resourceCulture
    0.59
    CodeAttribute
    0.58
    InputLabel
    0.58
    ess
    0.57
    Activations Density 0.022%

    No Known Activations