© 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. 4896
    Prev
    Next
    INDEX
    Explanations

    Technical/scientific content

    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
     '\\;'
    -0.75
    #
    -0.63
    Rüyada
    -0.63
    </tfoot>
    -0.62
    posedge
    -0.59
    DockStyle
    -0.58
    ніципалі
    -0.57
    makeatother
    -0.57
    φέρει
    -0.56
    ็
    -0.56
    POSITIVE LOGITS
     négociations
    0.66
     dieux
    0.65
     mêmes
    0.59
     pouvoirs
    0.56
     tâches
    0.55
     científicas
    0.53
     leçons
    0.52
     pères
    0.52
     hoogte
    0.51
     vérit
    0.51
    Activations Density 0.002%

    No Known Activations