© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 3953
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to the act of removing or deletion

    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
    AsUp
    -0.88
    fao
    -0.80
     bArr
    -0.72
    日语
    -0.72
    Cordialement
    -0.71
     Schuster
    -0.69
    });*/
    -0.69
    Портал
    -0.68
    躇
    -0.68
    };*/
    -0.67
    POSITIVE LOGITS
     removals
    1.43
     Removal
    1.41
     REMOVE
    1.38
     Removed
    1.36
     removal
    1.33
     Remove
    1.33
     removed
    1.30
    Remove
    1.30
     REMOV
    1.30
     Removes
    1.29
    Activations Density 0.094%

    No Known Activations