© 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. 821
    Prev
    Next
    INDEX
    Explanations

    computer code-related error messages and medical terminology.

    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
    Życiorys
    -0.46
    utscher
    -0.40
    zerland
    -0.39
    hlungen
    -0.36
    sschutz
    -0.35
    ACC
    -0.35
     Cister
    -0.35
    τή
    -0.34
    НИК
    -0.34
     Pind
    -0.33
    POSITIVE LOGITS
     E
    1.35
    E
    1.29
    getE
    1.07
    エ
    1.02
    Ｅ
    1.00
     É
    0.97
     Ee
    0.96
     EE
    0.96
     EB
    0.96
     EP
    0.95
    Activations Density 3.803%

    No Known Activations