© 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. 1-RES-MATRYOSHKA-DC
    7. 106
    Prev
    Next
    INDEX
    Explanations

    code snippets involving C preprocessor directives and language syntax

    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
    ########.
    -0.77
    aarrggbb
    -0.60
     itſelf
    -0.60
     nõ
    -0.58
    esque
    -0.53
     oprot
    -0.53
     saati
    -0.50
    SizeMode
    -0.49
     Shakspeare
    -0.49
     mukana
    -0.49
    POSITIVE LOGITS
    endphp
    1.14
    varargin
    0.73
     lateinit
    0.70
     elseif
    0.69
    __':
    0.69
     AssemblyTitle
    0.69
    abstractmethod
    0.68
    thenReturn
    0.68
    Życiorys
    0.68
     %>%
    0.68
    Activations Density 16.026%

    No Known Activations