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. 26700
    Prev
    Next
    INDEX
    Explanations

    occurrences of color specifications in the text

    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
    s
    -0.56
    سخ
    -0.50
    々に
    -0.49
    》.
    -0.48
     marqués
    -0.48
    ʃ
    -0.48
     SPOT
    -0.47
     Roskov
    -0.47
    Parcelize
    -0.47
     sexuales
    -0.46
    POSITIVE LOGITS
     متعلقه
    0.90
    IntoConstraints
    0.88
    PyExc
    0.80
    orianCalendar
    0.77
     cref
    0.75
    ädie
    0.75
    providedIn
    0.74
    OrNil
    0.73
     wireType
    0.73
    lossians
    0.69
    Activations Density 0.001%

    No Known Activations