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. 26034
    Prev
    Next
    INDEX
    Explanations

    gene names and their associated expressions in a biological context

    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
    alem
    -0.45
     وبعد
    -0.43
    énario
    -0.43
    cision
    -0.43
     виправивши
    -0.43
    onday
    -0.43
    drawSprites
    -0.39
    ument
    -0.39
    izard
    -0.38
     affinch
    -0.38
    POSITIVE LOGITS
     WaitForSeconds
    0.73
    DockStyle
    0.71
    migrationBuilder
    0.71
    StoryboardSegue
    0.71
     AppBundle
    0.69
    VIAF
    0.69
    IntoConstraints
    0.69
    Espèce
    0.68
    +#+
    0.68
    GenerationType
    0.64
    Activations Density 0.018%

    No Known Activations