© 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. 14965
    Prev
    Next
    INDEX
    Explanations

    references to substances or materials that are absorbed or capable of absorbing substances

    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
     adsorbed
    -0.89
     adsorption
    -0.79
     Absorption
    -0.79
     absorption
    -0.78
     Adsorption
    -0.73
     Factbook
    -0.72
    ftagPool
    -0.71
    Absorption
    -0.68
    absorbed
    -0.68
    absorption
    -0.63
    POSITIVE LOGITS
     absorbing
    1.86
    absorbing
    1.48
     absorb
    1.21
     absorbs
    1.10
     absorbers
    1.10
     absorbent
    1.05
     absorber
    0.99
     Absor
    0.92
    Absor
    0.85
    absorb
    0.85
    Activations Density 0.002%

    No Known Activations