© 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. 14344
    Prev
    Next
    INDEX
    Explanations

    values

    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
     विश्वसनीयता
    -0.49
     parteci
    -0.49
     Voy
    -0.49
    fromnode
    -0.48
    Values
    -0.46
    me
    -0.46
    Mia
    -0.46
    帖最后由
    -0.45
     sár
    -0.45
     roble
    -0.45
    POSITIVE LOGITS
     "..\..\..\
    0.72
    Personendaten
    0.66
    SourceChecksum
    0.56
     "..\..\
    0.54
    Parcelize
    0.53
    brigens
    0.53
     shenan
    0.53
    MIDDLEWARE
    0.49
    idak
    0.48
     unknownFields
    0.48
    Activations Density 0.113%

    No Known Activations