© 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. 1-CLT-HP
    7. 506
    Prev
    Next
    INDEX
    Explanations

    fo

    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
    FO
    -1.55
    fo
    -1.30
     FO
    -1.09
    Fo
    -1.02
     Fo
    -0.91
     disambiguazione
    -0.82
     fo
    -0.74
    fos
    -0.71
     تضيفلها
    -0.71
     tartalomajánló
    -0.66
    POSITIVE LOGITS
     tour
    0.47
    ArgsConstructor
    0.46
     Kerk
    0.46
    plash
    0.45
    brand
    0.44
    AdapterView
    0.43
     brand
    0.42
    ælp
    0.42
    NonNull
    0.41
    orski
    0.41
    Activations Density 0.158%

    No Known Activations