© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 30202
    Prev
    Next
    INDEX
    Explanations

    phrases related to consent and agreement regarding terms and policies

    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
    CodeAttribute
    -0.93
     itſelf
    -0.88
     ſche
    -0.84
     iſt
    -0.83
    SequentialGroup
    -0.83
    Попис
    -0.82
    AnimationsModule
    -0.79
     Anfitrión
    -0.79
     ſtill
    -0.78
     Monfieur
    -0.78
    POSITIVE LOGITS
     
    0.49
    <eos>
    0.46
     into
    0.45
    abase
    0.43
     sorte
    0.42
     to
    0.42
    стройки
    0.42
     gọn
    0.41
     an
    0.41
     себя
    0.41
    Activations Density 0.007%

    No Known Activations