© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 40723
    Prev
    Next
    INDEX
    Explanations

    be

    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
     الحره
    -0.62
    ly
    -0.56
     profiler
    -0.46
     legitimacy
    -0.46
    <>();
    -0.46
     documentation
    -0.45
    Parcelize
    -0.45
    isOk
    -0.44
     implantation
    -0.44
    /.
    -0.43
    POSITIVE LOGITS
     Roskov
    0.73
    holding
    0.70
    fitting
    0.69
     tarko
    0.69
    ⓧ
    0.69
    verwijspagina
    0.67
    headings
    0.65
    oredCriteria
    0.64
    friends
    0.64
     dispuestos
    0.63
    Activations Density 0.028%

    No Known Activations