Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 39662
    Prev
    Next
    INDEX
    Explanations

    Aller

    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
    ysh
    -0.71
    aroos
    -0.68
    t
    -0.63
    at
    -0.59
     Whitney
    -0.59
    hauser
    -0.57
    n
    -0.56
    r
    -0.52
    ar
    -0.51
    z
    -0.51
    POSITIVE LOGITS
     Мексичка
    0.69
    ſelf
    0.65
    tvguidetime
    0.64
     myſelf
    0.64
     виправивши
    0.64
     itſelf
    0.62
    новниш
    0.61
    enterOuterAlt
    0.60
    ſelves
    0.59
    OGND
    0.59
    Activations Density 0.316%

    No Known Activations