© 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. 13038
    Prev
    Next
    INDEX
    Explanations

    Chemical contexts

    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
     Vit
    -0.97
    Vit
    -0.89
     vit
    -0.88
     VIT
    -0.78
    VIT
    -0.65
    vit
    -0.64
    Derp
    -0.56
    MENAFN
    -0.54
     vitamina
    -0.51
    Individual
    -0.50
    POSITIVE LOGITS
    setVerticalGroup
    0.65
     Efq
    0.62
    contentLoaded
    0.60
     Jefus
    0.59
     Chrift
    0.59
    PyExc
    0.56
     متعلقه
    0.55
     Hift
    0.54
     Mots
    0.54
     Chrif
    0.53
    Activations Density 0.103%

    No Known Activations