© 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. 72496
    Prev
    Next
    INDEX
    Explanations

    Random snippets of text

    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
     الحره
    -0.65
    stateMutability
    -0.61
    NameInMap
    -0.59
    Personendaten
    -0.57
    MigrationBuilder
    -0.54
    ++]
    -0.51
    pushFollow
    -0.49
     '\\;'
    -0.49
    EndProject
    -0.47
    ++);
    -0.47
    POSITIVE LOGITS
     hard
    0.74
     long
    0.68
     old
    0.59
    long
    0.57
     HARD
    0.55
    mergeFrom
    0.55
     lie
    0.54
    Contributors
    0.54
    ,
    0.52
     sweat
    0.52
    Activations Density 0.000%

    No Known Activations