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. 9487
    Prev
    Next
    INDEX
    Explanations

    technical specifications related to angles and measurements

    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
    Personensuche
    -0.69
     استنادى
    -0.69
    ########.
    -0.68
    NewUrlParser
    -0.64
    offsetof
    -0.61
     дописавши
    -0.60
     spinning
    -0.59
    KommentareTeilen
    -0.59
    quels
    -0.59
     rotors
    -0.59
    POSITIVE LOGITS
     houſe
    0.65
     againſt
    0.65
     uſ
    0.65
     uſed
    0.65
     Jefus
    0.64
     myſelf
    0.63
     Anſ
    0.62
     juſt
    0.60
     ſur
    0.59
    ſelves
    0.58
    Activations Density 0.032%

    No Known Activations