© 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. 5-CLT-HP
    7. 94499
    Prev
    Next
    INDEX
    Explanations

    ch

    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
    virons
    -0.46
    NESS
    -0.45
     helst
    -0.45
    tillo
    -0.41
     inimigos
    -0.41
     ifrån
    -0.39
     jueces
    -0.39
    psum
    -0.38
    parse
    -0.38
    frutar
    -0.38
    POSITIVE LOGITS
    WithIOException
    0.80
    rungsseite
    0.79
    webElementXpaths
    0.78
     Roskov
    0.74
     BoxDecoration
    0.73
    EndGlobalSection
    0.73
     myſelf
    0.73
    TypedDataSet
    0.71
    parsedMessage
    0.71
    addCriterion
    0.71
    Activations Density 0.000%

    No Known Activations