© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-RES-MATRYOSHKA-DC
    7. 1578
    Prev
    Next
    INDEX
    Explanations

    words ending in "ation", "ion", or other Latinate suffixes indicating a state, quality, or action

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.24.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.24.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
    ু
    -0.43
    AndEndTag
    -0.42
     ومل
    -0.38
    roc
    -0.38
    cmp
    -0.37
    equilibrio
    -0.37
    ########.
    -0.36
    skrä
    -0.34
    lø
    -0.34
    urd
    -0.34
    POSITIVE LOGITS
    ating
    1.39
    ations
    1.30
    ated
    1.29
    ates
    1.19
    ators
    1.19
    ator
    1.13
    ATING
    1.09
    ATED
    1.06
    ative
    1.05
    ational
    1.01
    Activations Density 0.533%

    No Known Activations