© 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. 2380
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistical results related to studies or analyses

    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
    /'.$
    -0.58
    Composable
    -0.54
    切
    -0.50
    SourceChecksum
    -0.48
    BASEPATH
    -0.47
     that
    -0.44
     “
    -0.44
    торая
    -0.44
    #+#
    -0.43
    kool
    -0.42
    POSITIVE LOGITS
    yntaxException
    0.76
    AndEndTag
    0.76
     beginnetje
    0.74
    تفصیلات
    0.72
     myſelf
    0.70
    InjectAttribute
    0.70
    BufferException
    0.69
    AddTagHelper
    0.69
    NewUrlParser
    0.68
    meneu
    0.63
    Activations Density 0.069%

    No Known Activations