© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 13277
    Prev
    Next
    INDEX
    Explanations

    gene/protein

    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
     Diony
    -0.62
    ########.
    -0.59
    VIAF
    -0.54
    riwal
    -0.53
    yarnpkg
    -0.52
    mapStateToProps
    -0.52
    InstanceState
    -0.50
     @"";
    -0.49
    laszt
    -0.48
    =$((
    -0.48
    POSITIVE LOGITS
    SourceChecksum
    0.52
     newOwner
    0.48
     linkovi
    0.47
     rétro
    0.47
    uing
    0.47
     Gees
    0.46
    RunAsync
    0.46
     antigen
    0.45
    rinology
    0.45
    IndentedString
    0.45
    Activations Density 0.012%

    No Known Activations