© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 11043
    Prev
    Next
    INDEX
    Explanations

    phrases related to health and safety concerns

    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
    expandindo
    -1.02
    ſelves
    -0.89
     ſeveral
    -0.81
     Majefty
    -0.80
    Personensuche
    -0.77
    ſelf
    -0.77
     Houſe
    -0.76
     Efq
    -0.76
     "");
    -0.75
     Anſ
    -0.75
    POSITIVE LOGITS
     avena
    0.45
    во
    0.45
     canela
    0.45
     di
    0.45
     wind
    0.42
    tières
    0.40
     life
    0.40
     to
    0.40
     of
    0.37
     leven
    0.37
    Activations Density 0.085%

    No Known Activations