© 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. 3745
    Prev
    Next
    INDEX
    Explanations

    measurements of infrared light absorption

    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
     Catch
    -0.78
     catch
    -0.76
     CATCH
    -0.74
    CATCH
    -0.73
    Catch
    -0.72
    catch
    -0.70
     getItemCount
    -0.70
     caught
    -0.69
     CreateTagHelper
    -0.67
     Quanti
    -0.65
    POSITIVE LOGITS
     absorption
    3.11
     Absorption
    2.98
    Absorption
    2.72
     absorb
    2.64
     absorbed
    2.61
    absorption
    2.59
     absorbs
    2.55
     absorbing
    2.48
     Absor
    2.48
     absor
    2.34
    Activations Density 0.033%

    No Known Activations