© 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. 20-CLT-HP
    7. 77330
    Prev
    Next
    INDEX
    Explanations

    Time frame

    np_max-act-logits · 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
     transfieras
    -0.68
    SafeMath
    -0.63
    queryInterface
    -0.61
     виправивши
    -0.60
    URLException
    -0.60
    GenerationType
    -0.59
    ########.
    -0.58
    utilisons
    -0.57
    GeoNames
    -0.56
    leſs
    -0.56
    POSITIVE LOGITS
    __':
    0.45
     kau
    0.44
    OGND
    0.44
     المعيارى
    0.44
     decade
    0.42
    ox
    0.42
     pass
    0.41
    ern
    0.41
     X
    0.40
    なんでも
    0.39
    Activations Density 0.000%

    No Known Activations