© 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. 11089
    Prev
    Next
    INDEX
    Explanations

    mentions of parabolic or paraboloid structures, often referring to a component or characteristic of a device or concept

    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
     perd
    -0.54
    ക്ഷ
    -0.49
    UnknownFieldSet
    -0.47
    DockStyle
    -0.47
     EdgeInsets
    -0.47
     consig
    -0.46
    urez
    -0.46
    mender
    -0.46
     tiket
    -0.46
     Kamb
    -0.46
    POSITIVE LOGITS
     parabolic
    3.70
    abolic
    2.48
     parabola
    2.19
     parab
    1.70
    parab
    1.52
    Parab
    1.36
     Parab
    1.32
     hyperbolic
    0.72
    cookieParser
    0.71
    PerformLayout
    0.69
    Activations Density 0.001%

    No Known Activations