© 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. 18489
    Prev
    Next
    INDEX
    Explanations

    references to mirrors and mirror-like properties or characteristics

    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
     himo
    -0.81
     препратки
    -0.81
    Ged
    -0.69
     flav
    -0.68
    lahan
    -0.68
     Manfred
    -0.68
    Manfred
    -0.66
    Sqft
    -0.65
     Fot
    -0.65
     Wils
    -0.65
    POSITIVE LOGITS
     mirror
    1.42
     Mirrors
    1.38
     Mirror
    1.36
     mirrors
    1.23
    Mirrors
    1.23
     MIRROR
    1.20
    Mirror
    1.16
    mirror
    1.09
     Spiegel
    1.02
     miroir
    0.98
    Activations Density 0.005%

    No Known Activations