© 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. 3128
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ab
    -0.67
    ong
    -0.66
     Alegre
    -0.61
    ter
    -0.60
    tr
    -0.60
    <em>
    -0.59
    ag
    -0.59
    つけた
    -0.59
    <strong>
    -0.58
    sc
    -0.57
    POSITIVE LOGITS
    +#+#
    1.00
     resourceCulture
    0.91
    ]")]
    0.90
    #:
    0.87
    SOUNDBITE
    0.80
    +#+
    0.79
    #+#
    0.78
     himo
    0.78
     CreateTagHelper
    0.77
    Zeneca
    0.77
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.