Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 7
    Prev
    Next
    INDEX
    Explanations

    wall

    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
     wall
    -1.58
     Wall
    -1.45
    Wall
    -1.41
    wall
    -1.30
     WALL
    -1.18
     walls
    -1.09
     Walls
    -1.08
    WALL
    -1.01
    Walls
    -0.91
    walls
    -0.88
    POSITIVE LOGITS
    ValueStyle
    0.72
     CGRectMake
    0.61
    menes
    0.61
     setInterval
    0.60
     sportif
    0.59
    URLException
    0.59
    новништво
    0.59
    quelize
    0.58
    TintMode
    0.57
     suprême
    0.57
    Activations Density 0.016%

    No Known Activations