© 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. 1-CLT-HP
    7. 13844
    Prev
    Next
    INDEX
    Explanations

    not

    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
     larmes
    -0.69
     lisäksi
    -0.63
     preuves
    -0.60
     bénéfices
    -0.59
     pertes
    -0.59
     épaules
    -0.56
     leçons
    -0.56
     télécharge
    -0.56
     démocr
    -0.54
     lèvres
    -0.54
    POSITIVE LOGITS
    RTLD
    0.71
    SerializedSize
    0.68
     allu
    0.68
    memoized
    0.68
     <=",
    0.67
    MemoryWarning
    0.66
    aarrggbb
    0.65
     myſelf
    0.65
     betweenstory
    0.63
     itſelf
    0.63
    Activations Density 0.324%

    No Known Activations