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. 9913
    Prev
    Next
    INDEX
    Explanations

    negative assessments or criticisms related to various subjects

    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
     autorytatywna
    -0.80
    inander
    -0.67
    ритори
    -0.63
    énario
    -0.59
     hinweg
    -0.57
    fattning
    -0.57
     humeur
    -0.57
     isolado
    -0.56
    tahui
    -0.55
    eiras
    -0.55
    POSITIVE LOGITS
    Hozzáférés
    0.68
     houſe
    0.68
    neſs
    0.63
     Jefus
    0.63
     ſmall
    0.62
     purpoſe
    0.60
    SuppressLint
    0.60
     snippetHide
    0.60
     Alten
    0.60
    بوابة
    0.59
    Activations Density 0.073%

    No Known Activations