© 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. 12-RES-MATRYOSHKA-DC
    7. 28504
    Prev
    Next
    INDEX
    Explanations

    mentions of texture and its variations

    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
    autoreleasepool
    -0.88
    IsMutable
    -0.79
    PhysRevD
    -0.77
     Neale
    -0.74
     canary
    -0.73
     Efq
    -0.73
    ">—
    -0.73
    IFORNIA
    -0.73
    iestety
    -0.72
    gatsby
    -0.71
    POSITIVE LOGITS
    TEXTURE
    1.24
     Texture
    1.23
    Texture
    1.20
    texture
    1.19
     texture
    1.16
     Textures
    1.16
     textures
    1.12
    Textures
    1.09
    textures
    1.05
    setTexture
    0.79
    Activations Density 0.003%

    No Known Activations