© 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. 20-CLT-HP
    4. 74937
    Prev
    Next
    INDEX
    Explanations

    collections

    np_max-act-logits · 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
     esternos
    -0.86
     للمعارف
    -0.79
     ujednoznacz
    -0.70
    ConstraintMaker
    -0.66
    +#+
    -0.65
    BufferException
    -0.65
    徊
    -0.65
    ineno
    -0.65
     HasFactory
    -0.65
    verwijspagina
    -0.65
    POSITIVE LOGITS
     workforce
    0.46
     Forward
    0.45
     通販
    0.44
    forward
    0.42
     forward
    0.41
     collection
    0.39
    従
    0.39
    col
    0.38
    multicolumn
    0.38
    AddHtmlAttribute
    0.38
    Activations Density 0.000%

    No Known Activations