© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 91040
    Prev
    Next
    INDEX
    Explanations

    ucle

    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
     Efq
    -0.89
    WarningLevel
    -0.87
    ngdoc
    -0.84
    thmetic
    -0.82
     tartalomajánló
    -0.81
     Majefty
    -0.81
    AntiForgeryToken
    -0.78
    stuffs
    -0.78
    abetes
    -0.77
    tvguidetime
    -0.77
    POSITIVE LOGITS
    e
    0.44
     At
    0.42
    锈钢
    0.41
     un
    0.41
     the
    0.39
     Using
    0.39
    Using
    0.39
    g
    0.39
     /
    0.38
    це
    0.37
    Activations Density 0.305%

    No Known Activations