© 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. 1149
    Prev
    Next
    INDEX
    Explanations

    strings of letters that include the letter "e", especially if they are adjacent to each other, and words with the suffix "ine" or prefixes be/fe.

    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
    ness
    -1.50
    nya
    -1.32
    name
    -0.96
    d
    -0.90
    not
    -0.81
    ों
    -0.79
    so
    -0.78
    了
    -0.78
    night
    -0.77
    sy
    -0.77
    POSITIVE LOGITS
    eeee
    0.56
    eeeeeeee
    0.53
    e
    0.53
    eee
    0.50
    eeeee
    0.50
    eeeeee
    0.47
    vents
    0.45
    InputBorder
    0.43
    iro
    0.43
    ffect
    0.41
    Activations Density 2.780%

    No Known Activations