© 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. 0-CLT-HP
    7. 43285
    Prev
    Next
    INDEX
    Explanations

    technical texts

    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
     ujednoznacz
    -0.84
    protoimpl
    -0.76
    extAlignment
    -0.68
    PhysRev
    -0.67
    rxjs
    -0.63
    ReusableCell
    -0.63
    anterie
    -0.63
    UpInside
    -0.62
    mybatisplus
    -0.62
    tiously
    -0.60
    POSITIVE LOGITS
     '\\;'
    0.60
     CreateTagHelper
    0.56
     sighed
    0.47
    uens
    0.45
    shad
    0.45
     created
    0.44
    BeginContext
    0.44
     rico
    0.43
     mengenal
    0.42
     compro
    0.42
    Activations Density 0.053%

    No Known Activations