© 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. 40699
    Prev
    Next
    INDEX
    Explanations

    forgiven

    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
    parsedMessage
    -0.67
    ly
    -0.65
    i
    -0.59
    BeginContext
    -0.54
    quins
    -0.52
    istered
    -0.52
    all
    -0.49
    ApiModel
    -0.48
    quis
    -0.47
    ništ
    -0.47
    POSITIVE LOGITS
    LEGGI
    0.67
     myſelf
    0.65
    lottes
    0.60
    PreInfinity
    0.59
    FTFY
    0.59
    ésus
    0.59
     Reſ
    0.59
    itoneal
    0.58
    évaluateur
    0.58
    UAGE
    0.57
    Activations Density 0.066%

    No Known Activations