© 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. 0-RES-MATRYOSHKA-DC
    7. 10811
    Prev
    Next
    INDEX
    Explanations

    references or mentions of block quotes or quotation markers

    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
    ronpa
    -0.82
     يتيمه
    -0.80
     Ã
    -0.74
     fl
    -0.73
    fl
    -0.71
    yntaxException
    -0.70
    AsUp
    -0.69
    tagHelperRunner
    -0.67
    <h5>
    -0.64
     fi
    -0.63
    POSITIVE LOGITS
    '''
    2.86
     '''
    2.39
    '''
    2.16
    </b>
    1.46
    ''')
    1.34
    </i>
    1.33
    ''',
    1.32
    ('''
    1.26
    ''''
    1.23
    <b>
    1.07
    Activations Density 0.000%

    No Known Activations