© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1789
    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
     adicionais
    -0.56
     väh
    -0.56
     suun
    -0.50
     näky
    -0.49
     adicionales
    -0.49
     comienzos
    -0.49
     deberes
    -0.49
     tirantes
    -0.49
     lèvres
    -0.49
     žiad
    -0.49
    POSITIVE LOGITS
    RenderAtEndOf
    0.76
     tartalomajánló
    0.75
    AndEndTag
    0.71
    })->
    0.71
    jsonwebtoken
    0.69
    ChildScrollView
    0.69
    TestingModule
    0.68
    Personensuche
    0.67
    tagext
    0.67
    JspWriter
    0.65
    Activations Density 0.000%

    No Known Activations