© 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. 12-RES-MATRYOSHKA-DC
    7. 22933
    Prev
    Next
    INDEX
    Explanations

    terms related to absorption or absorbent materials

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    west
    -0.67
     Landis
    -0.65
    烷
    -0.62
     Mun
    -0.61
    Mun
    -0.61
     mun
    -0.60
    abend
    -0.59
    omethane
    -0.58
    y
    -0.57
     McKenzie
    -0.56
    POSITIVE LOGITS
     Absor
    1.54
    Absor
    1.31
     absorb
    1.30
     Absorb
    1.30
     Absorption
    1.27
     absorbs
    1.24
     absorbing
    1.23
    absor
    1.21
    absorb
    1.21
    absorbed
    1.20
    Activations Density 0.010%

    No Known Activations