© 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. 9724
    Prev
    Next
    INDEX
    Explanations

    legal disclaimers and conditions regarding information sharing and privacy

    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
     propOrder
    -0.85
     doInBackground
    -0.82
    CodedInputStream
    -0.70
    tonsoft
    -0.64
    Sedangkan
    -0.60
    vety
    -0.60
    Biographie
    -0.60
     Soak
    -0.59
     IBRARY
    -0.59
    stood
    -0.58
    POSITIVE LOGITS
    ]^{-
    0.49
    ీ
    0.45
     cần
    0.45
     requiere
    0.42
     rendre
    0.42
    gis
    0.41
    deauna
    0.41
    Un
    0.40
     kurie
    0.40
     nahilalakip
    0.40
    Activations Density 0.013%

    No Known Activations