© 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. 4-CLT-HP
    7. 4395
    Prev
    Next
    INDEX
    Explanations

    articles

    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
    cydow
    -0.66
    DataTypes
    -0.63
    cokinetics
    -0.59
     Offisielt
    -0.57
    FunctionFlags
    -0.57
     octaves
    -0.56
    BlockSize
    -0.56
     ſeveral
    -0.56
    ](#
    -0.56
    enumii
    -0.56
    POSITIVE LOGITS
    osoba
    0.52
    utilisons
    0.51
     person
    0.50
    afficheront
    0.48
    object
    0.48
     object
    0.48
    someone
    0.45
     adott
    0.45
    inguém
    0.45
     personne
    0.45
    Activations Density 0.002%

    No Known Activations