© 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. 1-CLT-HP
    4. 515
    Prev
    Next
    INDEX
    Explanations

    allegations

    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
     allegations
    -0.98
     allegation
    -0.84
     accusations
    -0.82
     accusation
    -0.73
    rénées
    -0.50
    ial
    -0.44
    thorpe
    -0.44
    gh
    -0.44
     المعيارى
    -0.41
    zaam
    -0.40
    POSITIVE LOGITS
    ItemBackground
    0.96
     Pompeii
    0.77
     Efq
    0.76
    TintMode
    0.75
    IInterface
    0.71
    ">—
    0.71
    EDEFAULT
    0.70
     levelled
    0.70
     MenuView
    0.69
    oredCriteria
    0.69
    Activations Density 0.006%

    No Known Activations