© 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. 98271
    Prev
    Next
    INDEX
    Explanations

    scientific research

    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
     disambiguazione
    -0.79
    новниш
    -0.76
    uxxxx
    -0.74
    CppMethod
    -0.66
     initComponents
    -0.65
    pédie
    -0.61
     }}"></
    -0.60
     }?>
    -0.59
    Tikang
    -0.58
     насељу
    -0.58
    POSITIVE LOGITS
    ogno
    0.43
     cao
    0.42
    :///
    0.42
    ANCO
    0.42
    EMPL
    0.42
    ponible
    0.41
    اده
    0.41
     COUNTER
    0.40
    Czym
    0.40
    ائن
    0.40
    Activations Density 0.010%

    No Known Activations