© 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. 18-RES-MATRYOSHKA-DC
    7. 874
    Prev
    Next
    INDEX
    Explanations

    numerical values with symbols like $ and exponents

    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.18.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.18.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
     to
    -0.65
     und
    -0.62
     im
    -0.60
     k
    -0.60
    <eos>
    -0.59
     ${
    -0.58
    ThroughAttribute
    -0.58
     di
    -0.58
    rfloor
    -0.57
     K
    -0.57
    POSITIVE LOGITS
     myſelf
    1.44
     itſelf
    1.41
     Anſ
    1.35
     pleaſure
    1.30
     Jefus
    1.24
     ſy
    1.23
     Houſe
    1.20
     ſtate
    1.20
     Majefty
    1.18
     Monfieur
    1.18
    Activations Density 0.836%

    No Known Activations