Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 19728
    Prev
    Next
    INDEX
    Explanations

    instances of references or citations in the document

    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
    bkz
    -0.60
    ]').
    -0.59
    @[+][
    -0.58
    )$/,
    -0.54
    makeText
    -0.54
     woj
    -0.53
    )}
    -0.53
    )](
    -0.53
    saraba
    -0.52
    InjectAttribute
    -0.50
    POSITIVE LOGITS
     Majefty
    0.76
     Monfieur
    0.75
     ſever
    0.72
     صوتيه
    0.72
     ddelweddau
    0.70
     متعلقه
    0.69
     uſe
    0.69
     Shakspeare
    0.68
     Perſ
    0.66
     Reſ
    0.64
    Activations Density 0.016%

    No Known Activations