© 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. 11000
    Prev
    Next
    INDEX
    Explanations

    evaluative markers indicating measurement of an intervention’s impact

    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
    opardy
    -0.63
    पया
    -0.62
    xtick
    -0.61
     concor
    -0.59
    orkin
    -0.56
     implicated
    -0.51
    params
    -0.50
    Geographie
    -0.50
    ocry
    -0.49
    Miy
    -0.49
    POSITIVE LOGITS
     effectiveness
    1.77
     Effectiveness
    1.63
    Effectiveness
    1.41
    effectiveness
    1.38
    Sucesor
    0.98
    IVENESS
    0.71
    ::~
    0.68
    lessness
    0.65
    InjectAttribute
    0.63
    hésite
    0.60
    Activations Density 0.001%

    No Known Activations