© 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. 0-CLT-HP
    7. 94300
    Prev
    Next
    INDEX
    Explanations

    title

    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
     title
    -1.71
    title
    -1.13
     titles
    -1.07
     título
    -1.02
     titel
    -1.00
     titre
    -0.90
     Titel
    -0.84
     Title
    -0.81
     premise
    -0.81
    Title
    -0.81
    POSITIVE LOGITS
    脚注の使い方
    0.97
     Roskov
    0.97
    SequentialGroup
    0.93
     ainfi
    0.92
     referenties
    0.82
     pleaſure
    0.82
    rungsseite
    0.81
     auffi
    0.81
    DockStyle
    0.80
     SIMBAD
    0.79
    Activations Density 0.157%

    No Known Activations