© 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. 140
    Prev
    Next
    INDEX
    Explanations

    words related to making decisions or expressing opinions, either through building, study, or agreement

    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
     Meksiku
    -0.68
    bewerken
    -0.67
     незавершена
    -0.64
    AnchorStyles
    -0.63
    verwijspagina
    -0.62
    AndEndTag
    -0.60
    ējās
    -0.57
     >=",
    -0.54
    StoryboardSegue
    -0.53
    licherweise
    -0.52
    POSITIVE LOGITS
     on
    3.19
     على
    1.43
     на
    1.41
     On
    1.34
     auf
    1.32
    On
    1.26
     روی
    1.24
    on
    1.20
     på
    1.20
     trên
    1.18
    Activations Density 4.325%

    No Known Activations