© 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. 6352
    Prev
    Next
    INDEX
    Explanations

    technical terms related to braking systems and measurements

    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
    ArgsConstructor
    -0.49
    TabIndex
    -0.48
    querque
    -0.43
    cur
    -0.42
    Przypisy
    -0.42
    Trama
    -0.42
     متحده
    -0.41
    found
    -0.40
    INSTANCE
    -0.39
     본
    -0.39
    POSITIVE LOGITS
    +:+
    0.66
     Paglinawan
    0.64
    Jereo
    0.62
     kasarigan
    0.59
    inaison
    0.57
     bénéficiaire
    0.56
     Administrativna
    0.56
    DOCTYPE
    0.55
     itself
    0.54
    ktı
    0.53
    Activations Density 1.251%

    No Known Activations