© 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. 5-CLT-HP
    7. 93320
    Prev
    Next
    INDEX
    Explanations

    }\

    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
    Kjelder
    -0.56
    postmedia
    -0.55
    Portail
    -0.54
    contentLoaded
    -0.52
    astify
    -0.52
    PYX
    -0.50
    országban
    -0.50
     bağlantılar
    -0.50
    SpringBootTest
    -0.49
     kompati
    -0.49
    POSITIVE LOGITS
    aarrggbb
    0.63
     African
    0.56
     Africans
    0.51
    sonian
    0.50
     individuals
    0.49
     people
    0.48
     ausz
    0.48
    choke
    0.47
     Virgin
    0.47
    NESS
    0.47
    Activations Density 0.002%

    No Known Activations