© 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. 24-RES-MATRYOSHKA-DC
    7. 40
    Prev
    Next
    INDEX
    Explanations

    the word "as" when used as a preposition or conjunction, and often activates on text containing scientific phrasing or discussion of studies.

    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
    Not in Any Lists

    No Comments

    Negative Logits
    TagMode
    -0.84
     surla
    -0.71
     Administrativna
    -0.71
    poptosis
    -0.69
    клопе
    -0.67
    +#+#
    -0.67
     Italijanski
    -0.66
    enderror
    -0.65
    testens
    -0.65
    хьтан
    -0.65
    POSITIVE LOGITS
     a
    3.39
     an
    2.44
     another
    1.34
     something
    1.11
     eine
    1.07
     the
    1.06
     einen
    1.06
     einer
    1.05
     sebuah
    1.05
    a
    1.05
    Activations Density 11.554%

    No Known Activations