© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 2172
    Prev
    Next
    INDEX
    Explanations

    time

    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
    BeginContext
    -1.05
    MLLoader
    -0.72
    +#+#
    -0.71
    DoubleQuotes
    -0.65
     '\\;'
    -0.64
    Clik
    -0.64
    GraphicsUnit
    -0.64
    oplayer
    -0.61
    abestanden
    -0.60
    BeginInit
    -0.60
    POSITIVE LOGITS
    queryInterface
    0.47
    kwds
    0.47
    diyesi
    0.45
    NCF
    0.41
     fon
    0.39
    vespa
    0.38
    bnf
    0.37
     fre
    0.37
    nisse
    0.37
     Stein
    0.36
    Activations Density 0.000%

    No Known Activations