© 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. 1263
    Prev
    Next
    INDEX
    Explanations

    language related to arguments and presenting ideas, especially in online discussions.

    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
    specialchars
    -0.57
     typelib
    -0.56
    Karakter
    -0.54
    FetchType
    -0.54
    DispatchToProps
    -0.52
    IndentedString
    -0.52
    ENOMEM
    -0.50
    userdetails
    -0.50
    харак
    -0.49
    getTemplate
    -0.49
    POSITIVE LOGITS
     verifiable
    1.14
     verified
    1.13
     disprove
    1.11
     verify
    1.05
     confirmed
    1.02
     corroborated
    1.02
     confirmation
    1.02
     conclusive
    1.02
     substantiated
    1.01
     evidence
    1.00
    Activations Density 1.929%

    No Known Activations