© 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. 45767
    Prev
    Next
    INDEX
    Explanations

    Code and technical documents

    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
     StatefulWidget
    -0.83
     StatelessWidget
    -0.76
     BoxDecoration
    -0.76
    SharedDtor
    -0.71
    LookAnd
    -0.69
     consultato
    -0.67
     rospy
    -0.65
    GEBURTSDATUM
    -0.64
    новништво
    -0.60
    Morfologia
    -0.60
    POSITIVE LOGITS
    ManyToMany
    0.45
    :✨
    0.45
    お楽しみに
    0.45
    FieldNumber
    0.44
     territory
    0.43
    oneofs
    0.42
    setTarget
    0.42
    Océ
    0.41
    пле
    0.41
    Sus
    0.41
    Activations Density 0.015%

    No Known Activations