© 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. 28278
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistical results

    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
    principalTable
    -0.91
     slutt
    -0.87
     '\\;'
    -0.83
     henvis
    -0.81
     feroit
    -0.80
    +#+
    -0.79
    +#+#
    -0.78
     thermique
    -0.78
    fromnode
    -0.77
    LabelTagHelper
    -0.77
    POSITIVE LOGITS
     g
    0.47
     post
    0.45
    serviceWorker
    0.44
     pass
    0.44
     dos
    0.44
     s
    0.42
     Covid
    0.42
     nog
    0.40
     Do
    0.39
     Pass
    0.39
    Activations Density 0.010%

    No Known Activations