© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 2125
    Prev
    Next
    INDEX
    Explanations

    Code/Technical documentation

    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
    gentes
    -0.46
    acetic
    -0.42
    iz
    -0.41
    Configurer
    -0.41
    ay
    -0.40
     Fu
    -0.40
     NUKAT
    -0.39
    autorest
    -0.39
    _->
    -0.39
     memu
    -0.38
    POSITIVE LOGITS
    AndEndTag
    0.75
    ंदीखरीदारी
    0.73
    %</
    0.71
    ########.
    0.66
    رشف
    0.66
    tagHelperRunner
    0.63
     فريبيس
    0.63
    rshire
    0.63
     BorderSide
    0.63
    tvguidetime
    0.63
    Activations Density 0.001%

    No Known Activations