© 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. 373
    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
    ercises
    -0.66
    ⓧ
    -0.58
    IsContent
    -0.56
    Према
    -0.54
     Chriftian
    -0.52
    Zitat
    -0.52
     protegido
    -0.51
     espirituales
    -0.50
    estroyer
    -0.50
     MonoBehaviour
    -0.49
    POSITIVE LOGITS
    ArgsConstructor
    0.55
    orn
    0.55
    olerance
    0.51
    aur
    0.50
    rus
    0.50
     time
    0.49
    elan
    0.47
     each
    0.46
    цездатний
    0.46
    Controllo
    0.46
    Activations Density 0.204%

    No Known Activations