© 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. 3882
    Prev
    Next
    INDEX
    Explanations

    sections of technical or scientific documentation

    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
    HomeAsUpEnabled
    -0.72
     McColl
    -0.67
    OrNil
    -0.65
    IPAC
    -0.60
    cherichia
    -0.59
     Stearns
    -0.59
     Saxe
    -0.57
    ริง
    -0.56
    }{||
    -0.56
    ().__
    -0.55
    POSITIVE LOGITS
     Ins
    3.33
    Ins
    3.23
    ins
    3.06
     ins
    3.00
    INS
    2.48
     INS
    2.39
     insulation
    1.93
     insulating
    1.89
     Insulation
    1.70
     insulator
    1.70
    Activations Density 0.044%

    No Known Activations