© 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
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 13324
    Prev
    Next
    INDEX
    Explanations

    output related to computer code or programming instructions

    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
    nativeElement
    -0.69
    enumii
    -0.65
     consultato
    -0.64
    Revenir
    -0.64
    ButterKnife
    -0.64
     ujednoznacz
    -0.63
    LEncoder
    -0.62
    enumi
    -0.61
    +#+#
    -0.60
    origins
    -0.60
    POSITIVE LOGITS
    original
    0.95
    IPC
    0.70
    ngdoc
    0.69
    üy
    0.65
     Signalez
    0.59
    ORIGINAL
    0.58
    Solución
    0.55
     kry
    0.54
    aros
    0.54
    ISupport
    0.54
    Activations Density 0.035%

    No Known Activations