© 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. 425
    Prev
    Next
    INDEX
    Explanations

    hexadecimal strings, especially those that appear to be identifiers or keys

    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
    y
    -1.36
    e
    -1.34
    a
    -1.29
    i
    -1.26
    u
    -1.24
    s
    -1.19
    t
    -1.18
    o
    -1.18
    es
    -1.01
    l
    -1.00
    POSITIVE LOGITS
    сё
    0.36
    mybatisplus
    0.36
     Cliquez
    0.33
    blers
    0.32
    vettes
    0.31
     lèvres
    0.31
    épaisseur
    0.31
     Voyez
    0.31
    Opéra
    0.31
    Egypte
    0.30
    Activations Density 5.152%

    No Known Activations