© 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. 92393
    Prev
    Next
    INDEX
    Explanations

    butter

    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
    Espèce
    -0.83
     ostavi
    -0.75
    findpost
    -0.70
    SPATH
    -0.69
    expandindo
    -0.67
    SuppressMessage
    -0.67
    ViewFeatures
    -0.66
    homonymie
    -0.66
     مشين
    -0.65
     Roskov
    -0.65
    POSITIVE LOGITS
    flies
    0.49
    ed
    0.48
     defStyleAttr
    0.44
    flying
    0.43
     néglig
    0.41
     menyeb
    0.40
     hâte
    0.39
    发表于
    0.38
     pasti
    0.36
     lourdes
    0.36
    Activations Density 0.001%

    No Known Activations