© 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. 0-RES-MATRYOSHKA-DC
    7. 10930
    Prev
    Next
    INDEX
    Explanations

    expressions or descriptions related to maximal values or peaks

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    owanego
    -0.69
     ExecuteAsync
    -0.66
     ProtoMessage
    -0.65
    parsedMessage
    -0.65
    esía
    -0.63
    WithIOException
    -0.62
    SourceChecksum
    -0.61
    UrlResolution
    -0.61
     quies
    -0.60
    cessive
    -0.60
    POSITIVE LOGITS
     maximal
    2.34
     Maximal
    1.96
    maximal
    1.78
    WriteLiteral
    0.50
    เส
    0.50
    imal
    0.50
     maxim
    0.47
    canActivate
    0.46
    ViewChild
    0.46
     ober
    0.45
    Activations Density 0.001%

    No Known Activations