© 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. 4332
    Prev
    Next
    INDEX
    Explanations

    was

    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
    __);
    -0.62
     ujednoznacz
    -0.51
    其
    -0.48
     تانيه
    -0.48
     resourceCulture
    -0.47
    はその
    -0.47
     VizieR
    -0.47
     annuelle
    -0.46
    omock
    -0.45
     الرياضيه
    -0.44
    POSITIVE LOGITS
    mergeFrom
    0.63
     purpoſe
    0.59
     CreateTagHelper
    0.59
     poffe
    0.57
     firſt
    0.56
     raiſ
    0.54
     فريبيس
    0.54
    ásra
    0.54
     not
    0.53
     ſtill
    0.53
    Activations Density 0.002%

    No Known Activations