© 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. 1-CLT-HP
    7. 9809
    Prev
    Next
    INDEX
    Explanations

    hyphens

    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
    styleType
    -0.56
     fidélité
    -0.56
    RemoveField
    -0.56
     judiciales
    -0.54
     honte
    -0.54
     plongée
    -0.54
     autorité
    -0.52
     illustrazione
    -0.51
     verificación
    -0.51
     maintien
    -0.50
    POSITIVE LOGITS
     mxArray
    0.52
     rotary
    0.50
     bezeichneter
    0.50
    ']);
    0.49
     distro
    0.45
    sci
    0.45
     Bucure
    0.45
    ὴν
    0.45
     capes
    0.45
     dynam
    0.45
    Activations Density 0.068%

    No Known Activations