© 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. 0-CLT-HP
    7. 1239
    Prev
    Next
    INDEX
    Explanations

    directions and/or pain

    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
     EClass
    -0.84
     DIRECTION
    -0.83
     directions
    -0.80
     direction
    -0.76
    featureID
    -0.75
     itſelf
    -0.71
    directions
    -0.69
    NUMX
    -0.69
    direction
    -0.69
    izations
    -0.69
    POSITIVE LOGITS
    StructEnd
    0.49
    omyia
    0.45
     javax
    0.44
     for
    0.43
    FormTagHelper
    0.43
    .
    0.42
    Luego
    0.41
    Versus
    0.41
     Primarily
    0.40
    !
    0.40
    Activations Density 0.012%

    No Known Activations