© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1828
    Prev
    Next
    INDEX
    Explanations

    relationships and disputes

    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
    /${
    -0.50
     noise
    -0.50
    erdan
    -0.47
     uns
    -0.45
    IGENCE
    -0.45
     nasty
    -0.44
     dama
    -0.43
     bad
    -0.43
     danger
    -0.43
     terrible
    -0.43
    POSITIVE LOGITS
     autorytatywna
    0.77
    Autoritní
    0.71
    +#+
    0.71
    principalColumn
    0.69
    MessageOf
    0.68
    FunctionFlags
    0.67
    LookAnd
    0.67
    ंदीखरीदारी
    0.65
     فريبيس
    0.63
    ochial
    0.62
    Activations Density 0.003%

    No Known Activations