© 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. 1-CLT-HP
    7. 14208
    Prev
    Next
    INDEX
    Explanations

    uthor

    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
    NOPQRST
    -0.47
     مشين
    -0.47
     Swartz
    -0.46
     मध्य
    -0.45
     Murray
    -0.45
     Meredith
    -0.44
     rapi
    -0.44
     kiri
    -0.42
     CORE
    -0.42
     τοῦ
    -0.42
    POSITIVE LOGITS
    uxxxx
    0.72
     مرئيه
    0.66
    StoryboardSegue
    0.66
    GIVEREF
    0.60
    UnsafeEnabled
    0.59
    extAlignment
    0.59
    \{\\
    0.58
     NSCoder
    0.57
     frischen
    0.57
    CppMethod
    0.57
    Activations Density 0.019%

    No Known Activations