© 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. 1-CLT-HP
    7. 14736
    Prev
    Next
    INDEX
    Explanations

    technical writing/programming

    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
     sail
    -0.66
     isKindOfClass
    -0.60
     snippetHide
    -0.58
     MediaQuery
    -0.56
    saraba
    -0.55
     sails
    -0.53
     فريبيس
    -0.53
     FontWeight
    -0.51
    ங்க
    -0.50
    outState
    -0.50
    POSITIVE LOGITS
     ostavi
    0.66
     OMITBAD
    0.57
     препратки
    0.57
    BufferException
    0.57
    ::$_
    0.51
     <=",
    0.50
    XmlAttribute
    0.50
     laget
    0.50
    בודה
    0.50
    etwork
    0.49
    Activations Density 0.012%

    No Known Activations