© 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. 4-CLT-HP
    7. 2539
    Prev
    Next
    INDEX
    Explanations

    developed

    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
    таратура
    -0.48
     ogóle
    -0.47
     %>%
    -0.47
    大家好
    -0.44
     to
    -0.42
     cherchés
    -0.42
    versity
    -0.42
    selves
    -0.41
     autorytatywna
    -0.41
     slik
    -0.41
    POSITIVE LOGITS
     a
    0.73
     ideas
    0.61
     the
    0.60
     what
    0.60
    nocache
    0.57
     interest
    0.57
    ReusableCell
    0.56
    Сылтамалар
    0.56
    __(/*!
    0.56
    ofür
    0.55
    Activations Density 0.012%

    No Known Activations