© 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. 4-CLT-HP
    7. 860
    Prev
    Next
    INDEX
    Explanations

    or

    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
    Hentet
    -0.67
     autorytatywna
    -0.56
     disambiguazione
    -0.55
    PreferredItem
    -0.53
     Paglinawan
    -0.49
    󠁢
    -0.47
    ItemBackground
    -0.46
     ddelweddau
    -0.46
    UnsafeEnabled
    -0.45
    IsContent
    -0.44
    POSITIVE LOGITS
     propOrder
    0.96
    AutoScaleMode
    0.62
    ExecuteNonQuery
    0.58
     results
    0.57
     specify
    0.57
    ;
    0.56
    complexContent
    0.56
     obtains
    0.56
    satunya
    0.55
     result
    0.55
    Activations Density 0.012%

    No Known Activations