© 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
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 208
    Prev
    Next
    INDEX
    Explanations

    concepts related to moral dilemmas and the nature of good and evil

    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
     Cleo
    -0.67
     Bue
    -0.65
     Shr
    -0.62
    rungsseite
    -0.60
    mitglied
    -0.60
    éfono
    -0.60
    #+#
    -0.57
    ⮕
    -0.57
    bcryptjs
    -0.57
    帖最后由
    -0.57
    POSITIVE LOGITS
     invokingState
    0.85
     contextLoads
    0.84
     estekak
    0.78
    انجليز
    0.78
     azzurro
    0.77
    <h2>
    0.73
     PopupWindow
    0.73
     تضيفلها
    0.71
     Bowls
    0.71
     Adm
    0.71
    Activations Density 2.413%

    No Known Activations