© 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. 5-CLT-HP
    7. 92207
    Prev
    Next
    INDEX
    Explanations

    code and technical writing

    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
    OGND
    -0.68
     للاسماء
    -0.61
    المناصب
    -0.59
     beginnetje
    -0.59
     mouseY
    -0.58
    #)
    -0.57
     صوتيه
    -0.56
     noDo
    -0.56
    rrggbb
    -0.56
    cienza
    -0.54
    POSITIVE LOGITS
    SourceChecksum
    0.50
     yym
    0.50
     mạch
    0.46
    istert
    0.44
    ma
    0.44
    dtm
    0.41
    MessageTagHelper
    0.40
     Tatum
    0.40
     Kit
    0.39
     national
    0.39
    Activations Density 0.000%

    No Known Activations