© 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. 4342
    Prev
    Next
    INDEX
    Explanations

    references to attacks and related actions or themes

    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
    गु
    -0.70
    /**
    -0.70
     ύ
    -0.63
     whole
    -0.61
    Tril
    -0.61
    drv
    -0.61
     possibility
    -0.60
    ρίου
    -0.60
    för
    -0.60
    ǒ
    -0.60
    POSITIVE LOGITS
     Attack
    1.72
     ATTACK
    1.61
     Attacks
    1.56
    Attacks
    1.55
    ATTACK
    1.54
     attack
    1.49
     attacks
    1.48
    attacks
    1.45
    Attack
    1.40
    attack
    1.40
    Activations Density 0.054%

    No Known Activations