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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 45633
    Prev
    Next
    INDEX
    Explanations

    rolls

    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
    rolls
    -1.58
    roll
    -1.44
    ROLL
    -1.04
    rungsseite
    -0.80
    Rolls
    -0.76
     pinulongan
    -0.69
    rolle
    -0.66
    Roll
    -0.65
     rolls
    -0.65
    rolla
    -0.62
    POSITIVE LOGITS
    ië
    0.50
     ويكيميديا
    0.50
     Zeeland
    0.48
     object
    0.45
     BoxFit
    0.44
    esine
    0.43
    object
    0.42
    vcut
    0.42
    ی
    0.42
     postales
    0.41
    Activations Density 0.299%

    No Known Activations