© 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. 5-CLT-HP
    7. 2200
    Prev
    Next
    INDEX
    Explanations

    forEach

    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
     varandra
    -0.67
     hiér
    -0.64
     mourut
    -0.63
     élevées
    -0.61
     bénévoles
    -0.61
     élas
    -0.61
     fermés
    -0.60
     thérape
    -0.60
     actuelles
    -0.60
     refroidissement
    -0.58
    POSITIVE LOGITS
    Personendaten
    0.75
    Varint
    0.60
     murmur
    0.57
    bootstrapcdn
    0.56
     autorytatywna
    0.55
     tropical
    0.55
     hypot
    0.55
    BASEPATH
    0.55
     cache
    0.54
    LookAnd
    0.54
    Activations Density 0.000%

    No Known Activations