© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 41817
    Prev
    Next
    INDEX
    Explanations

    directions

    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
     directions
    -2.34
     Directions
    -1.95
    directions
    -1.78
    Directions
    -1.67
     DIRECTIONS
    -1.45
     danger
    -1.41
    DIRECTIONS
    -1.20
     Danger
    -1.10
     instructions
    -1.05
     Direction
    -1.02
    POSITIVE LOGITS
     in
    0.60
    ,
    0.56
    wall
    0.56
     from
    0.52
    base
    0.50
     of
    0.48
    -
    0.47
     on
    0.47
    list
    0.46
    ware
    0.45
    Activations Density 1.667%

    No Known Activations