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. 11535
    Prev
    Next
    INDEX
    Explanations

    references to specific growth factors and their subtypes in biological contexts

    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
     von
    -0.51
    فس
    -0.49
     Merid
    -0.49
     kli
    -0.47
     skol
    -0.47
     kamp
    -0.47
     Gilli
    -0.47
    ItemName
    -0.47
     ske
    -0.46
     Bones
    -0.46
    POSITIVE LOGITS
     tfsi
    0.88
     fevere
    0.88
     estimés
    0.87
    SerializedSize
    0.84
     itſelf
    0.84
    ########.
    0.83
    sizeCache
    0.82
    migrationBuilder
    0.81
     ſever
    0.81
    الحياه
    0.79
    Activations Density 0.005%

    No Known Activations