© 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. 20-CLT-HP
    4. 74523
    Prev
    Next
    INDEX
    Explanations

    Random text snippets

    np_max-act-logits · 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
     less
    -0.59
     weniger
    -0.52
     mniej
    -0.49
     eigentlich
    -0.49
     not
    -0.49
    apimachinery
    -0.48
    complexType
    -0.48
    not
    -0.47
    Abitanti
    -0.45
    хь
    -0.45
    POSITIVE LOGITS
     well
    0.77
     WELL
    0.64
    StoryboardSegue
    0.60
    WELL
    0.59
    well
    0.58
    èvres
    0.58
     يتيمه
    0.57
    Personensuche
    0.57
     ComVisible
    0.56
    حياتها
    0.54
    Activations Density 0.000%

    No Known Activations