© 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. 77238
    Prev
    Next
    INDEX
    Explanations

    common

    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
    LookAnd
    -0.72
     CharSequence
    -0.60
     darte
    -0.59
     liggen
    -0.57
    jmniej
    -0.57
     Explicit
    -0.56
     disambiguazione
    -0.56
    Neat
    -0.56
    Explicit
    -0.55
    المكان
    -0.55
    POSITIVE LOGITS
     common
    0.80
    common
    0.61
     com
    0.59
    ContentAsync
    0.51
     commons
    0.49
     comm
    0.47
    WriteBarrier
    0.47
    coff
    0.44
     común
    0.44
     COMMON
    0.44
    Activations Density 0.001%

    No Known Activations