© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 92807
    Prev
    Next
    INDEX
    Explanations

    illary

    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
     createContext
    -0.48
    iseksi
    -0.42
    uride
    -0.36
    Festival
    -0.35
     dolgo
    -0.35
     хранения
    -0.35
     |
    -0.35
     cancelar
    -0.35
    saco
    -0.34
     Festival
    -0.33
    POSITIVE LOGITS
    Portail
    0.79
    ArgsConstructor
    0.74
     Belles
    0.73
    ftagPool
    0.71
     onAnimation
    0.70
    EndContext
    0.70
    MENAFN
    0.68
    HomeAsUpEnabled
    0.68
     noDo
    0.67
    jspx
    0.67
    Activations Density 0.001%

    No Known Activations