© 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. 8685
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "darkness."

    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
    osoever
    -0.90
    λέον
    -0.74
    oneofs
    -0.72
    isseurs
    -0.71
    djangoproject
    -0.71
    mfrac
    -0.71
     AssemblyTitle
    -0.70
    onee
    -0.68
    hány
    -0.66
     obstante
    -0.65
    POSITIVE LOGITS
     DARK
    1.40
    DARK
    1.31
     Dark
    1.30
    darkness
    1.20
    Dark
    1.20
     dark
    1.15
     Darkness
    1.13
    dark
    1.07
     darkness
    1.07
    Darkness
    1.04
    Activations Density 0.010%

    No Known Activations