© 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. 4800
    Prev
    Next
    INDEX
    Explanations

    Code/Syntax

    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
    idopsis
    -0.70
    AsUp
    -0.62
    OGND
    -0.61
    APOLIS
    -0.60
     Anſ
    -0.60
    évaluateur
    -0.60
    AdapterFactory
    -0.60
    Москва
    -0.59
     الحره
    -0.58
     iya
    -0.58
    POSITIVE LOGITS
    WaitGroup
    0.65
    TestingModule
    0.52
     περι
    0.46
    PostExecute
    0.45
    __*/
    0.44
    Calling
    0.43
     >=",
    0.41
    ttp
    0.41
    WebMethod
    0.40
     henvis
    0.39
    Activations Density 0.000%

    No Known Activations