© 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. 76488
    Prev
    Next
    INDEX
    Explanations

    coding/math context

    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
    Personendaten
    -0.63
     للمعارف
    -0.60
     незавершена
    -0.60
     <>",
    -0.55
    ,
    -0.54
    Diwedd
    -0.51
    Élet
    -0.50
     fallen
    -0.48
     hands
    -0.47
     personne
    -0.47
    POSITIVE LOGITS
    endphp
    0.62
    AndEndTag
    0.60
    RTGC
    0.59
    Mule
    0.57
     SwitchCompat
    0.57
    IMPORTED
    0.56
    VolleyError
    0.55
    "}>
    0.55
    GTCX
    0.55
    Capítulo
    0.55
    Activations Density 0.001%

    No Known Activations