© 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
    2. Gemma-2-2B
    3. 4-CLT-HP
    4. 4645
    Prev
    Next
    INDEX
    Explanations

    medical and technological advancements

    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
    ніципалі
    -0.64
    
    -0.64
    astify
    -0.64
    extAlignment
    -0.60
    IntoConstraints
    -0.60
     Efq
    -0.58
    pruch
    -0.57
    addGap
    -0.56
     civilisation
    -0.54
     Wicidata
    -0.54
    POSITIVE LOGITS
     and
    0.63
    TestBed
    0.57
    MigrationBuilder
    0.57
     or
    0.49
     démission
    0.48
    RTDA
    0.47
    SourceChecksum
    0.45
    ArgsConstructor
    0.45
     évalu
    0.44
    RunWith
    0.43
    Activations Density 0.004%

    No Known Activations