© 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. 4-CLT-HP
    7. 6
    Prev
    Next
    INDEX
    Explanations

    a

    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
     fhew
    -0.51
     helyez
    -0.50
    TypedArray
    -0.50
    stridium
    -0.49
     neceſſ
    -0.49
     ſtill
    -0.48
     purpoſe
    -0.47
     rivière
    -0.47
    Enlaces
    -0.46
     következő
    -0.45
    POSITIVE LOGITS
    AndEndTag
    0.73
    GEBURTSDATUM
    0.60
    ]")]
    0.59
     ddelweddau
    0.56
    enderror
    0.56
    Портал
    0.56
     חיצוניים
    0.55
     onAnimation
    0.54
    ControllerAdvice
    0.54
     tartalomajánló
    0.54
    Activations Density 0.010%

    No Known Activations