© 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. 20-CLT-HP
    7. 76600
    Prev
    Next
    INDEX
    Explanations

    coding/technical text

    np_max-act-logits · 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
    tvguidetime
    -0.73
     AssemblyTitle
    -0.73
    NameInMap
    -0.71
    RenderAtEndOf
    -0.68
    AnchorStyles
    -0.66
    iermark
    -0.66
     battre
    -0.65
     Meksiku
    -0.63
    SpringBootTest
    -0.63
    UniformLocation
    -0.63
    POSITIVE LOGITS
    DEZ
    0.42
     lenker
    0.40
     resourceCulture
    0.40
    eleste
    0.40
     rc
    0.39
     RC
    0.38
     requestCode
    0.37
    tonsoft
    0.36
     RCC
    0.36
    edic
    0.35
    Activations Density 0.000%

    No Known Activations