© 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. 30148
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to detectors and their functionality

    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
    we
    -0.63
    wechsel
    -0.61
     amphi
    -0.61
    خي
    -0.60
    nano
    -0.56
    ornis
    -0.56
     ourselves
    -0.56
     botanique
    -0.56
    bootstrapcdn
    -0.55
     Gibt
    -0.55
    POSITIVE LOGITS
     Detector
    0.93
     Detectors
    0.91
     detector
    0.91
     detectors
    0.90
    NOPQRST
    0.82
    detector
    0.81
    Detector
    0.73
     saurait
    0.68
    wpdb
    0.65
    ECTOR
    0.64
    Activations Density 0.020%

    No Known Activations