© 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. 20-CLT-HP
    4. 74746
    Prev
    Next
    INDEX
    Explanations

    -

    np_max-act-logits · 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
    ंदीखरीदारी
    -0.75
     الرياضيه
    -0.69
    DebuggerNonUser
    -0.60
    WindowConstants
    -0.59
    SourceChecksum
    -0.58
    IsContent
    -0.57
     Roskov
    -0.57
    FromArgb
    -0.56
    RenderAtEndOf
    -0.54
    orosi
    -0.52
    POSITIVE LOGITS
     diman
    0.52
    Portale
    0.52
     Tap
    0.48
    stino
    0.47
    HOLD
    0.47
    -
    0.47
    }?>
    0.46
    Patch
    0.46
    Tap
    0.45
    ніципалі
    0.45
    Activations Density 0.003%

    No Known Activations