© 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. 2-RES-MATRYOSHKA-DC
    7. 4353
    Prev
    Next
    INDEX
    Explanations

    snippets of text containing complex or technical information

    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
    Czytaj
    -0.60
    ACIO
    -0.58
    brać
    -0.57
     χρήση
    -0.55
    BASELINE
    -0.51
     regata
    -0.50
     dõi
    -0.49
    AJAS
    -0.49
    utate
    -0.49
    AZIONI
    -0.49
    POSITIVE LOGITS
    ScopeManager
    0.87
     }}"></
    0.84
    DebuggerNonUser
    0.76
    تقاوى
    0.75
    nloa
    0.74
    CloseOperation
    0.73
    })();
    0.68
     '\\;'
    0.68
    enumii
    0.67
     AssemblyProduct
    0.67
    Activations Density 0.626%

    No Known Activations