© 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. 95170
    Prev
    Next
    INDEX
    Explanations

    without

    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
     dispone
    -0.53
    +][
    -0.53
     Kome
    -0.51
     Италијани
    -0.50
    Autoritní
    -0.50
     cucharadita
    -0.50
    Jeografia
    -0.50
     rät
    -0.50
     vehe
    -0.49
    executor
    -0.48
    POSITIVE LOGITS
     my
    0.73
     why
    0.65
     where
    0.58
     who
    0.57
     when
    0.56
     being
    0.54
     saying
    0.53
     autorytatywna
    0.52
     part
    0.50
     our
    0.50
    Activations Density 0.011%

    No Known Activations