© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 45086
    Prev
    Next
    INDEX
    Explanations

    éné

    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
    hely
    -0.53
    éri
    -0.52
    nitz
    -0.52
    cases
    -0.51
    hya
    -0.50
     demons
    -0.45
     cases
    -0.44
    ual
    -0.44
    év
    -0.44
    digan
    -0.43
    POSITIVE LOGITS
    protoimpl
    0.98
    UnknownFieldSet
    0.94
    InjectAttribute
    0.90
    SharedDtor
    0.90
    PerformLayout
    0.86
    Попис
    0.82
    contentLoaded
    0.81
    homonymie
    0.79
    StoreMessageInfo
    0.79
    abestanden
    0.78
    Activations Density 0.187%

    No Known Activations