© 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. 45716
    Prev
    Next
    INDEX
    Explanations

    depending

    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
    __*/
    -0.69
     indietro
    -0.66
     femininas
    -0.64
     healthiest
    -0.62
     vectorielle
    -0.62
    olisme
    -0.61
    Geplaatst
    -0.60
     limpo
    -0.59
    رشف
    -0.59
    MemoryWarning
    -0.59
    POSITIVE LOGITS
    AddTagHelper
    0.57
    ValueStyle
    0.57
     ure
    0.54
     upor
    0.52
     Nave
    0.47
    UE
    0.46
    nal
    0.46
    AndEndTag
    0.46
     upp
    0.46
     appo
    0.45
    Activations Density 0.020%

    No Known Activations