© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 6459
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to safety

    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
     **)
    -0.81
     Protector
    -0.75
     McCulloch
    -0.75
     protection
    -0.74
     Protect
    -0.74
    ựng
    -0.74
     Marcello
    -0.73
    drück
    -0.73
    følgelig
    -0.73
     PROTECTION
    -0.72
    POSITIVE LOGITS
     Safe
    1.11
     unsafe
    1.10
     SAFE
    1.10
     safely
    1.09
     safe
    1.09
     safer
    1.05
    unsafe
    1.05
     safest
    1.03
    SAFE
    1.02
    Safe
    1.01
    Activations Density 0.026%

    No Known Activations