Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 15389
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to fire response and emergency management

    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
    tonsoft
    -0.82
    /**
    -0.80
     kaarangay
    -0.79
    httphttps
    -0.77
    WireFormatLite
    -0.77
    +#+#
    -0.75
    Datuak
    -0.74
     disambiguazione
    -0.73
    Jeografia
    -0.73
     kasarigan
    -0.72
    POSITIVE LOGITS
     момента
    0.47
     I
    0.44
    허
    0.41
     Verhältnis
    0.41
     unit
    0.40
     
    0.40
     protection
    0.39
    tahan
    0.39
     Zeitschrift
    0.39
     geeignet
    0.39
    Activations Density 0.690%

    No Known Activations