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. 32717
    Prev
    Next
    INDEX
    Explanations

    technical details related to radio broadcasting

    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
     HasFactory
    -0.67
    iastes
    -0.65
    APORE
    -0.62
    */;
    -0.61
    fromnode
    -0.61
    eseorang
    -0.59
    RTCF
    -0.57
    );*/
    -0.57
     AssemblyCompany
    -0.56
     CURIAM
    -0.56
    POSITIVE LOGITS
    likte
    0.50
     obeys
    0.50
    ustain
    0.49
     cadmium
    0.49
     obey
    0.48
    tagHelper
    0.48
    ינוך
    0.48
    pting
    0.47
    饱
    0.47
    fordern
    0.46
    Activations Density 0.004%

    No Known Activations