© 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. 12240
    Prev
    Next
    INDEX
    Explanations

    bly

    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
    bly
    -1.75
    rably
    -0.74
    FailureListener
    -0.71
    bitField
    -0.71
    MLLoader
    -0.69
     Italij
    -0.65
     bly
    -0.65
    RTGC
    -0.63
     nakalista
    -0.61
     TextInputType
    -0.61
    POSITIVE LOGITS
     Kam
    0.45
     differences
    0.45
    Proceed
    0.44
    gras
    0.44
    ylate
    0.42
     Anderson
    0.42
     Proceed
    0.42
     XX
    0.42
     exposure
    0.42
    Datuak
    0.42
    Activations Density 0.044%

    No Known Activations