© 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. 5-CLT-HP
    7. 3371
    Prev
    Next
    INDEX
    Explanations

    code and databases

    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
    nocache
    -0.63
     وتسجيلات
    -0.63
     AssemblyCulture
    -0.59
     myſelf
    -0.59
    oredCriteria
    -0.59
     Paglinawan
    -0.59
     nahilalakip
    -0.58
     uſe
    -0.57
     preſent
    -0.56
    hasErrors
    -0.56
    POSITIVE LOGITS
     likely
    0.69
     Likely
    0.58
    Likely
    0.57
    Probably
    0.53
    likely
    0.53
    FXML
    0.52
     Probably
    0.52
    Forums
    0.51
     players
    0.50
     typ
    0.49
    Activations Density 0.000%

    No Known Activations