© 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
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 91286
    Prev
    Next
    INDEX
    Explanations

    Copyright and earning licenses

    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
     springfox
    -0.59
    ɕ
    -0.53
    Diwedd
    -0.49
    Rohy
    -0.47
     Italijani
    -0.46
    öny
    -0.44
    rini
    -0.43
    himu
    -0.43
    opi
    -0.43
    bkz
    -0.43
    POSITIVE LOGITS
    存于互联网档案馆
    0.64
     getchar
    0.60
    })`
    0.59
    KommentareTeilen
    0.59
     bienvenue
    0.57
     Akismet
    0.56
    ेक
    0.54
    ScopeManager
    0.53
    mybatisplus
    0.52
    دانشنامهٔ
    0.52
    Activations Density 0.017%

    No Known Activations