© 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. 1-CLT-HP
    4. 45712
    Prev
    Next
    INDEX
    Explanations

    changes

    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
     MainAxisSize
    -0.81
    rrggbb
    -0.79
    DebuggerNonUser
    -0.75
     Wikiseite
    -0.72
    UserScript
    -0.71
    phem
    -0.69
     يتيمه
    -0.68
    ьаж
    -0.67
     umgeben
    -0.66
    complexContent
    -0.65
    POSITIVE LOGITS
    Gi
    0.46
     Gi
    0.45
    gl
    0.44
     indisponible
    0.44
    NA
    0.42
    gen
    0.41
    unuz
    0.41
     your
    0.41
    il
    0.40
     cento
    0.40
    Activations Density 0.006%

    No Known Activations