© 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. 98090
    Prev
    Next
    INDEX
    Explanations

    code/licensing

    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
    ExtendWith
    -0.68
    GEBURTSDATUM
    -0.67
    rxjs
    -0.66
    AddTagHelper
    -0.61
    rawDesc
    -0.61
    ंदीखरीदारी
    -0.60
     transfieras
    -0.58
    esModule
    -0.57
    TintMode
    -0.56
    getDoctrine
    -0.55
    POSITIVE LOGITS
     personalise
    0.50
     bedo
    0.46
    }\|
    0.45
     ancor
    0.44
    hape
    0.43
     investigate
    0.43
    München
    0.43
     }:
    0.43
     personalize
    0.42
     Husbandry
    0.42
    Activations Density 0.038%

    No Known Activations