© 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. 97833
    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
    unico
    -0.53
    WithMany
    -0.52
     GoogleFonts
    -0.50
    textTheme
    -0.48
    getSeconds
    -0.48
     واح
    -0.46
    InputBorder
    -0.46
    tidaknya
    -0.46
    gdx
    -0.45
    getSystemService
    -0.45
    POSITIVE LOGITS
     resourceCulture
    0.77
    :✨
    0.66
    ⓧ
    0.65
    '][$
    0.64
    DebuggerStep
    0.58
    __":
    0.57
     Connelly
    0.56
    ритори
    0.55
     FetchType
    0.55
    unknownFields
    0.54
    Activations Density 0.004%

    No Known Activations