© 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. 5785
    Prev
    Next
    INDEX
    Explanations

    negative connotations related to avoidance and obstruction in various contexts

    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
     NSCoder
    -0.62
     tecnológicos
    -0.52
     étroite
    -0.52
    silueta
    -0.51
     réforme
    -0.50
     privados
    -0.50
    ؤية
    -0.49
     femininas
    -0.49
     privées
    -0.48
    CppMethod
    -0.47
    POSITIVE LOGITS
    MLLoader
    0.63
     excepted
    0.55
    __':
    0.55
    macar
    0.54
     midwives
    0.54
     *((
    0.53
    бота
    0.53
     GIPHY
    0.53
     accomplishments
    0.52
    IGraphics
    0.52
    Activations Density 0.496%

    No Known Activations