© 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. 20-CLT-HP
    7. 76697
    Prev
    Next
    INDEX
    Explanations

    academic papers

    np_max-act-logits · 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
    ứa
    -0.66
     lagoon
    -0.66
    ^(@)
    -0.66
     lagoons
    -0.64
     صوتيه
    -0.64
     spéciaux
    -0.63
     Dike
    -0.62
     individuality
    -0.61
     Lagoon
    -0.61
     Савезне
    -0.60
    POSITIVE LOGITS
    phol
    0.44
     Mol
    0.42
    atr
    0.40
    انجليز
    0.40
    izop
    0.38
     Interess
    0.37
    engah
    0.37
     pinulongan
    0.36
     invester
    0.36
    fract
    0.36
    Activations Density 0.090%

    No Known Activations