© 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. 0-CLT-HP
    7. 94935
    Prev
    Next
    INDEX
    Explanations

    identical or apparent

    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
     identical
    -0.84
     alternate
    -0.78
     Apparently
    -0.76
    Apparently
    -0.71
    identical
    -0.71
    apparently
    -0.70
     apparently
    -0.68
    alternate
    -0.68
    Alternate
    -0.64
     Alternate
    -0.63
    POSITIVE LOGITS
     kasarigan
    0.66
    feri
    0.66
    PickerController
    0.65
     getItemId
    0.65
    esgue
    0.61
    UPAC
    0.61
     boreal
    0.60
     Ima
    0.59
    íncia
    0.59
    clusal
    0.59
    Activations Density 0.127%

    No Known Activations