© 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. 4-CLT-HP
    7. 4463
    Prev
    Next
    INDEX
    Explanations

    outside

    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
    addPreferredGap
    -0.67
    Rhestr
    -0.60
    AnimationsModule
    -0.59
    RenderAtEndOf
    -0.57
    InputBorder
    -0.57
    GeneratedCode
    -0.57
    ])):
    -0.56
    InstanceState
    -0.56
    GeoNames
    -0.56
    ByteBuf
    -0.55
    POSITIVE LOGITS
    featureID
    0.59
    IsInitialized
    0.57
    __*/
    0.56
     members
    0.55
    ględ
    0.54
     that
    0.54
     blocs
    0.53
     districts
    0.52
     sectors
    0.50
     plantations
    0.50
    Activations Density 0.002%

    No Known Activations