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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 97406
    Prev
    Next
    INDEX
    Explanations

    July

    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
     tumor
    -0.86
     tumour
    -0.79
    glGen
    -0.76
    tumor
    -0.73
     tumors
    -0.72
     étoit
    -0.72
    Tikang
    -0.71
    ⓧ
    -0.71
    igshid
    -0.68
    logs
    -0.67
    POSITIVE LOGITS
    feinander
    0.59
    nser
    0.53
     Стра
    0.52
     Picchu
    0.52
    ever
    0.47
     fes
    0.47
     kHz
    0.47
    uestamente
    0.46
    kosh
    0.46
     patro
    0.45
    Activations Density 0.205%

    No Known Activations