© 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. 4324
    Prev
    Next
    INDEX
    Explanations

    the presence of descending curves, often in combination with ascending or flat curves

    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
     Mérimée
    -0.66
    unnitel
    -0.56
    Exciting
    -0.56
     Puck
    -0.55
    pushFollow
    -0.55
     VIAF
    -0.54
    出版年
    -0.54
    Puck
    -0.53
     Expressway
    -0.53
     daqui
    -0.53
    POSITIVE LOGITS
     descending
    2.56
     Desc
    2.53
     descend
    2.33
     descended
    2.27
     desc
    2.25
     DESC
    2.19
    desc
    2.17
     descends
    2.17
     descent
    2.14
    Descending
    2.13
    Activations Density 0.034%

    No Known Activations