© 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. 6316
    Prev
    Next
    INDEX
    Explanations

    references to empirical studies or data

    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
    WithIOException
    -0.84
     consultato
    -0.76
     '\\;'
    -0.66
    phem
    -0.61
     Référence
    -0.60
    providedIn
    -0.59
    jsdelivr
    -0.56
    Revenir
    -0.54
    ysuckle
    -0.54
    bootstrapcdn
    -0.54
    POSITIVE LOGITS
     empirical
    3.08
     Empirical
    2.86
    Empirical
    2.67
    empi
    2.56
     empirically
    2.50
     empiric
    1.85
     Emp
    1.35
     emp
    1.30
    Emp
    1.13
     emper
    1.13
    Activations Density 0.007%

    No Known Activations