© 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. 1059
    Prev
    Next
    INDEX
    Explanations

    local connections

    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
     armament
    -1.34
    Personendaten
    -0.81
    expandindo
    -0.77
     armaments
    -0.75
    TemporalType
    -0.68
     ProtoMessage
    -0.65
     محفوظة
    -0.61
    ftagPool
    -0.59
    awtextra
    -0.58
    providedIn
    -0.57
    POSITIVE LOGITS
     Shakspeare
    0.59
     Raoul
    0.55
    arium
    0.53
     comm
    0.53
     composed
    0.50
     ejecutivo
    0.50
    lick
    0.49
     comprised
    0.47
     Enrico
    0.47
     reflector
    0.47
    Activations Density 0.058%

    No Known Activations