© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-RES-MATRYOSHKA-DC
    7. 1544
    Prev
    Next
    INDEX
    Explanations

    mathematical relationships involving linearity and nonlinearity

    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
    Negative Logits
    ########.
    -0.57
    pulumi
    -0.55
    NameInMap
    -0.55
     vPvB
    -0.55
    __*/
    -0.54
    ()?;
    -0.53
    QMetaType
    -0.52
    ^(@)
    -0.52
    ſelf
    -0.51
     Drey
    -0.50
    POSITIVE LOGITS
     linear
    4.56
     Linear
    4.19
    linear
    4.06
    Linear
    3.98
     LINEAR
    3.59
     liné
    3.36
    线性
    3.00
    LINEAR
    2.98
     linearity
    2.80
     linearly
    2.73
    Activations Density 0.270%

    No Known Activations