© 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
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 12068
    Prev
    Next
    INDEX
    Explanations

    front

    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
     front
    -1.06
     Front
    -1.02
     FRONT
    -0.94
    FRONT
    -0.90
    Front
    -0.86
    front
    -0.86
     fronts
    -0.68
     depan
    -0.61
     frontline
    -0.57
     frontal
    -0.53
    POSITIVE LOGITS
    let
    0.59
     Italij
    0.58
    ing
    0.54
    als
    0.52
    setCellValue
    0.52
    .
    0.49
    ings
    0.49
    VARIABLES
    0.48
    ulados
    0.48
    alism
    0.48
    Activations Density 0.048%

    No Known Activations