© 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. 1032
    Prev
    Next
    INDEX
    Explanations

    French text where people are discussing computer isssues.

    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
    —
    -0.81
    ”—
    -0.78
    "—
    -0.66
     −
    -0.65
    −
    -0.63
    —,
    -0.59
    —“
    -0.58
    )—
    -0.57
    ‐
    -0.55
     می‌توانید
    -0.54
    POSITIVE LOGITS
     Ã
    1.13
    Ã
    1.04
    Â
    0.89
    Ă
    0.79
    AddTagHelper
    0.77
     =)
    0.76
    ?<
    0.73
    �
    0.73
     â
    0.71
     �
    0.71
    Activations Density 0.286%

    No Known Activations