© 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. 45560
    Prev
    Next
    INDEX
    Explanations

    Colonel

    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
    ides
    -0.49
    })$}
    -0.48
    istoitu
    -0.48
    scut
    -0.43
    ONY
    -0.43
    isle
    -0.43
    n
    -0.43
    zzle
    -0.42
     واس
    -0.42
    entown
    -0.42
    POSITIVE LOGITS
    gameserver
    0.88
    Autoritní
    0.85
    rungsseite
    0.76
    archiviato
    0.70
    يكب
    0.69
     iNdEx
    0.69
     kasarigan
    0.68
    AutoresizingMask
    0.65
     jLabel
    0.64
    RegressionTest
    0.64
    Activations Density 0.294%

    No Known Activations