© 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. 3951
    Prev
    Next
    INDEX
    Explanations

    the polynomial with the specified Norman bound

    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
     umana
    -0.71
     marbles
    -0.70
     căr
    -0.68
     bianche
    -0.67
     umane
    -0.65
    usercontent
    -0.65
     camicia
    -0.64
     dė
    -0.63
     américa
    -0.61
     păr
    -0.60
    POSITIVE LOGITS
     norm
    3.08
    norm
    2.66
    Norm
    2.36
     norms
    2.31
     Norm
    2.28
    norms
    2.05
     NORM
    1.58
    NORM
    1.49
     normative
    1.38
     norme
    1.32
    Activations Density 0.015%

    No Known Activations