© 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. 20-CLT-HP
    7. 72850
    Prev
    Next
    INDEX
    Explanations

    Moreover

    np_max-act-logits · 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
    featureID
    -0.83
    NOPQRST
    -0.78
    PostInfinity
    -0.77
     jsPsych
    -0.74
     cdti
    -0.73
     AttributeSet
    -0.72
    iconque
    -0.72
     للمعارف
    -0.72
     WebDriverWait
    -0.71
     }}"></
    -0.70
    POSITIVE LOGITS
     an
    0.70
     four
    0.52
     its
    0.46
    an
    0.46
     two
    0.45
     five
    0.44
     Lav
    0.44
    ot
    0.43
     three
    0.43
     Black
    0.43
    Activations Density 0.001%

    No Known Activations