© 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. 5-CLT-HP
    7. 95038
    Prev
    Next
    INDEX
    Explanations

    articles

    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
    LookAnd
    -0.69
    Personensuche
    -0.67
    AndroidJUnit
    -0.61
     [*]
    -0.60
    teries
    -0.57
    typeorm
    -0.57
    awtextra
    -0.54
    AddTagHelper
    -0.53
     "..\..\..\
    -0.53
     ͡°)
    -0.52
    POSITIVE LOGITS
     wall
    0.79
     walls
    0.78
     Walls
    0.73
     WALL
    0.59
    wall
    0.59
    walls
    0.59
    Wall
    0.58
     Wall
    0.58
    Walls
    0.56
     murs
    0.55
    Activations Density 0.002%

    No Known Activations