© 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. 3693
    Prev
    Next
    INDEX
    Explanations

    on

    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
    setVerticalGroup
    -0.59
    حوالہ
    -0.49
    Varför
    -0.46
    [@"
    -0.44
    providedIn
    -0.44
     why
    -0.44
     reasons
    -0.43
     tilbake
    -0.43
    তথ্য
    -0.43
    gitto
    -0.43
    POSITIVE LOGITS
    ComponentScan
    0.60
    AddTagHelper
    0.60
     Pickup
    0.57
     AssemblyCulture
    0.55
     Himo
    0.53
     Diagonal
    0.53
    )\}
    0.53
     Philos
    0.52
    +#+
    0.50
    kmäler
    0.50
    Activations Density 0.154%

    No Known Activations