© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 12542
    Prev
    Next
    INDEX
    Explanations

    references to the steepness or steep gradient of something

    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
     referenties
    -0.65
    }}^{(
    -0.57
     AssemblyCulture
    -0.52
     Schein
    -0.52
     réservés
    -0.52
     feu
    -0.49
    rostis
    -0.49
     apla
    -0.48
     digs
    -0.48
     الحره
    -0.48
    POSITIVE LOGITS
     steep
    3.25
     steeper
    2.42
     Steep
    2.11
     steeply
    1.77
    陡
    1.11
     stiff
    0.65
    󠁢
    0.65
     narrow
    0.64
     precipit
    0.64
     Magister
    0.61
    Activations Density 0.002%

    No Known Activations