© 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. 0-CLT-HP
    7. 44152
    Prev
    Next
    INDEX
    Explanations

    of

    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
     hundreds
    -0.82
     thousands
    -0.74
    ousands
    -0.71
     many
    -0.69
     Hundreds
    -0.68
     dozens
    -0.67
    hundreds
    -0.65
     Thousands
    -0.63
     reaſon
    -0.62
     countless
    -0.61
    POSITIVE LOGITS
     kasarigan
    0.75
     surla
    0.73
     mergeFrom
    0.68
    protoimpl
    0.68
    IVEREF
    0.66
     Chwiliwch
    0.63
    цездатний
    0.60
    WithIOException
    0.59
    __["
    0.59
     BoxDecoration
    0.58
    Activations Density 0.765%

    No Known Activations