© 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. 12-RES-MATRYOSHKA-DC
    7. 6361
    Prev
    Next
    INDEX
    Explanations

    phrases indicating methods or ways to accomplish tasks

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.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.12.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
    KommentareTeilen
    -0.75
     Italijani
    -0.63
     Vikipedi
    -0.63
    脚注の使い方
    -0.62
     nenhum
    -0.59
    expandindo
    -0.59
    Lähteet
    -0.57
    smithy
    -0.56
     tartalomajánló
    -0.56
     صوتيه
    -0.54
    POSITIVE LOGITS
    InjectAttribute
    0.67
    __(/*!
    0.64
     IBOutlet
    0.54
     insuffisamment
    0.53
    glVertex
    0.52
    openConnection
    0.52
     Rois
    0.51
    imbawa
    0.51
     notable
    0.51
    sibilities
    0.50
    Activations Density 0.348%

    No Known Activations