© 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
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 72056
    Prev
    Next
    INDEX
    Explanations

    Code/article snippets

    np_max-act-logits · 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
    errHandler
    -0.51
    fortawesome
    -0.41
     téléph
    -0.41
     čierna
    -0.40
    richTextPanel
    -0.40
     précédent
    -0.39
     intérieure
    -0.38
    로
    -0.37
     gehö
    -0.37
     '\\;'
    -0.37
    POSITIVE LOGITS
     AssemblyCulture
    0.82
    ⓧ
    0.76
    Obrázky
    0.72
     EconPapers
    0.70
    tvguidetime
    0.68
    IntoConstraints
    0.68
    ########.
    0.63
    XmlAccessorType
    0.63
     متعلقه
    0.63
    enumii
    0.62
    Activations Density 0.001%

    No Known Activations