© 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. 76574
    Prev
    Next
    INDEX
    Explanations

    code and technical snippets

    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
    fjspx
    -0.72
    __":
    -0.68
    extAlignment
    -0.66
    InputTagHelper
    -0.66
    uxxxx
    -0.65
     виправивши
    -0.65
    CppMethod
    -0.61
     resourceCulture
    -0.60
    RetentionPolicy
    -0.59
    SharedDtor
    -0.58
    POSITIVE LOGITS
     is
    1.00
    AllowUser
    0.47
     has
    0.45
    by
    0.44
    είται
    0.42
     richi
    0.42
     것이
    0.42
    liv
    0.41
     CURLOPT
    0.41
    IZONA
    0.41
    Activations Density 0.002%

    No Known Activations