© 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. 4-CLT-HP
    7. 977
    Prev
    Next
    INDEX
    Explanations

    need

    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
     unknownFields
    -0.82
    Autoritní
    -0.74
     समीक्षाओं
    -0.69
    Personendaten
    -0.65
    AsUp
    -0.61
     Pilate
    -0.59
    yntaxException
    -0.57
     AssemblyCulture
    -0.54
    +#+#
    -0.54
     Kome
    -0.53
    POSITIVE LOGITS
    adopted
    0.56
     adopted
    0.52
     définiti
    0.51
    supposed
    0.50
    Adopted
    0.50
     मैंने
    0.48
     inconnu
    0.47
    GetAxis
    0.47
     Adopted
    0.47
    PAIGN
    0.47
    Activations Density 0.023%

    No Known Activations