© 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. 1-CLT-HP
    7. 45559
    Prev
    Next
    INDEX
    Explanations

    oc

    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
    følgelig
    -0.56
    qrstuvwxyz
    -0.50
     rense
    -0.48
    SystemColors
    -0.48
    ertes
    -0.47
     povezave
    -0.46
     Blueprint
    -0.46
    Brainz
    -0.46
    eningen
    -0.46
     καρ
    -0.45
    POSITIVE LOGITS
    UnusedPrivate
    0.67
    BeginContext
    0.62
    DebuggerNonUser
    0.57
    __':
    0.57
    CastException
    0.54
     LoggerFactory
    0.54
    IContainer
    0.53
     ++)
    0.52
     kaynağından
    0.50
    ագրություններ
    0.50
    Activations Density 0.042%

    No Known Activations