© 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. 5-CLT-HP
    7. 93623
    Prev
    Next
    INDEX
    Explanations

    vitro

    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
     tartalomajánló
    -0.80
     ProtoMessage
    -0.76
    expandindo
    -0.69
    MigrationBuilder
    -0.65
     jScrollPane
    -0.61
    wäh
    -0.60
    ohyd
    -0.59
    ніципа
    -0.59
    kuuta
    -0.59
    PropertyChanging
    -0.58
    POSITIVE LOGITS
     Them
    0.63
     them
    0.53
     us
    0.48
     Results
    0.47
    them
    0.46
    Them
    0.45
     Benefits
    0.44
    ingroup
    0.42
     results
    0.42
     Also
    0.41
    Activations Density 0.003%

    No Known Activations