© 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. 1-RES-MATRYOSHKA-DC
    7. 1104
    Prev
    Next
    INDEX
    Explanations

    references to specific spectral analysis techniques, measurement data, or information related to IR and IP spectral features

    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
    CppMethod
    -0.66
    </thead>
    -0.65
    GOTREF
    -0.65
    ulatus
    -0.63
     commerciali
    -0.63
    Scénario
    -0.61
    Amérique
    -0.60
    Chham
    -0.59
    humanité
    -0.59
     Schwan
    -0.59
    POSITIVE LOGITS
     IR
    1.38
     IP
    1.34
     Inf
    1.27
     Ip
    1.21
     Institute
    1.20
     Infrared
    1.19
     Iron
    1.18
     Irons
    1.16
     Ir
    1.16
     INF
    1.16
    Activations Density 1.384%

    No Known Activations