© 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. 5-CLT-HP
    7. 1994
    Prev
    Next
    INDEX
    Explanations

    depends

    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
    AddTagHelper
    -0.73
    AxisAlignment
    -0.66
     InputDecoration
    -0.59
     you
    -0.53
     part
    -0.52
     Audiodateien
    -0.51
    ferenz
    -0.50
    DrawerToggle
    -0.49
     that
    -0.48
    estroyer
    -0.47
    POSITIVE LOGITS
    CONCURRENT
    0.52
     pantaloni
    0.52
    EnableWeb
    0.52
     seguente
    0.52
     indépendante
    0.51
     breathes
    0.50
     tryck
    0.50
     bílé
    0.50
     rencont
    0.49
    pendente
    0.49
    Activations Density 0.001%

    No Known Activations