© 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. 29677
    Prev
    Next
    INDEX
    Explanations

    phrases related to refutation or clarification of misconceptions

    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
    期刊论文
    -0.92
    ConstraintMaker
    -0.92
     EconPapers
    -0.91
    fjspx
    -0.85
    SourceChecksum
    -0.82
    adaptiveStyles
    -0.74
    PerformLayout
    -0.74
    Personendaten
    -0.73
    mybatisplus
    -0.73
     RISERV
    -0.70
    POSITIVE LOGITS
    したのは
    0.57
    ったのは
    0.54
    是因为
    0.48
     dom
    0.46
    because
    0.46
     שוליים
    0.45
    是因為
    0.45
     because
    0.43
    after
    0.43
     просто
    0.42
    Activations Density 0.265%

    No Known Activations