© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 5583
    Prev
    Next
    INDEX
    Explanations

    in

    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
    FontOfSize
    -0.84
     FetchType
    -0.81
    endphp
    -0.76
     препратки
    -0.75
     AssemblyVersion
    -0.67
    fillType
    -0.66
    EndContext
    -0.63
    MLLoader
    -0.61
    ArgsConstructor
    -0.60
    EDEFAULT
    -0.60
    POSITIVE LOGITS
     at
    0.54
     complètes
    0.46
     efectivos
    0.44
     oreilles
    0.40
     searching
    0.40
     ilma
    0.40
     âmes
    0.40
     attending
    0.40
     reviewing
    0.39
     piele
    0.39
    Activations Density 0.003%

    No Known Activations