© 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. 24-RES-MATRYOSHKA-DC
    7. 653
    Prev
    Next
    INDEX
    Explanations

    words, numbers, and symbols related to telephone and headset devices

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.24.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.24.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
    Abitanti
    -0.64
    IsContent
    -0.62
    SceneManagement
    -0.55
    udessa
    -0.55
     محفوظة
    -0.54
     Roskov
    -0.54
     autorytatywna
    -0.53
     للمعارف
    -0.53
    MLLoader
    -0.53
     OFDb
    -0.51
    POSITIVE LOGITS
     phone
    1.69
     telephone
    1.58
     call
    1.48
     calls
    1.47
     Phone
    1.41
     callers
    1.35
     Telephone
    1.34
     caller
    1.34
    phone
    1.32
    Calls
    1.31
    Activations Density 0.869%

    No Known Activations