© 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. 92672
    Prev
    Next
    INDEX
    Explanations

    scientific texts

    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
     useAppContext
    -0.77
     createSlice
    -0.59
    NewGuid
    -0.56
    ɵɵelementStart
    -0.55
    sidemargin
    -0.54
    ']?>
    -0.54
    MigrationBuilder
    -0.53
    HomeAsUpEnabled
    -0.53
    ஈ
    -0.52
    TagMode
    -0.52
    POSITIVE LOGITS
    tium
    0.52
    ogen
    0.45
     GENERATED
    0.44
    ীয়
    0.43
     Wiktionnaire
    0.43
     gäller
    0.42
     kỳ
    0.42
    preter
    0.42
    sträger
    0.42
     RATES
    0.41
    Activations Density 0.001%

    No Known Activations