© 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. 5664
    Prev
    Next
    INDEX
    Explanations

    trying

    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
    ’”
    -0.66
     analyse
    -0.63
     effet
    -0.61
    ')){
    -0.61
    ніципалі
    -0.60
    ‘’
    -0.60
     summarise
    -0.60
     resourceCulture
    -0.57
    ’.”
    -0.57
    ंदीखरीदारी
    -0.56
    POSITIVE LOGITS
    !—
    0.59
    opsida
    0.57
     esche
    0.56
    —
    0.55
     freakin
    0.54
    mdash
    0.53
     ça
    0.52
     nix
    0.52
    ?!?
    0.52
    .
    0.52
    Activations Density 0.015%

    No Known Activations