© 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. 3-RES-MATRYOSHKA-DC
    7. 2034
    Prev
    Next
    INDEX
    Explanations

    page break characters in legal documents

    oai_token-act-pair · gemini-2.0-flash
    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
    льга
    -0.51
     mystère
    -0.48
    ╦
    -0.47
     very
    -0.46
    xpath
    -0.46
    ktan
    -0.46
    sel
    -0.46
    zel
    -0.46
    ah
    -0.45
    ss
    -0.45
    POSITIVE LOGITS
    4.38
    -------
    1.17
    __":
    1.14
     '\\;'
    1.13
    endphp
    1.08
    __':
    1.07
    
    1.05
    __*/
    1.02
    tvguidetime
    1.02
    sizeCache
    1.00
    Activations Density 0.021%

    No Known Activations