© 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. 39792
    Prev
    Next
    INDEX
    Explanations

    fat

    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
    fat
    -1.72
    Fat
    -1.66
     Fat
    -1.63
     fat
    -1.60
     FAT
    -1.25
     Fats
    -1.20
    FAT
    -1.16
     Fatty
    -0.95
     fatty
    -0.92
    Fatty
    -0.82
    POSITIVE LOGITS
    ty
    0.69
    🏻
    0.68
    ness
    0.68
    tening
    0.66
    igable
    0.64
    textAppearance
    0.59
    alities
    0.58
    nagar
    0.58
    ities
    0.58
    rophes
    0.57
    Activations Density 0.095%

    No Known Activations