© 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. 95363
    Prev
    Next
    INDEX
    Explanations

    (=

    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
     aper
    -0.55
    TagHelpers
    -0.54
     point
    -0.52
     thereof
    -0.50
    ATTACHMENT
    -0.50
     rouleau
    -0.50
    icher
    -0.49
     mxArray
    -0.47
    \}.
    -0.47
    __;
    -0.46
    POSITIVE LOGITS
     GenerationType
    0.70
     JpaRepository
    0.68
    setVerticalGroup
    0.66
    dymyr
    0.63
     CommonModule
    0.60
    StoryboardSegue
    0.59
    écri
    0.59
    ">//
    0.59
    GEBURTSDATUM
    0.58
     صوتيه
    0.57
    Activations Density 0.245%

    No Known Activations