© 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. 1-CLT-HP
    7. 9621
    Prev
    Next
    INDEX
    Explanations

    s

    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
    NOWLEDG
    -0.43
    ientí
    -0.42
    spyOn
    -0.42
     مُعرِّف
    -0.42
     Ghana
    -0.41
    utches
    -0.41
     her
    -0.40
    RenderAtEndOf
    -0.40
     man
    -0.40
    +#+#
    -0.40
    POSITIVE LOGITS
    kloped
    0.73
    SBATCH
    0.73
    ----</
    0.69
     ویکی‌پدیای
    0.66
    #+#
    0.66
    seamnă
    0.65
     cucchia
    0.62
     fourrure
    0.62
     ffilm
    0.61
     setw
    0.61
    Activations Density 0.102%

    No Known Activations