© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 4879
    Prev
    Next
    INDEX
    Explanations

    phrases related to challenges and difficulties

    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
     VizieR
    -0.44
    ↵
    -0.44
    .
    -0.44
     seriously
    -0.44
    Gambas
    -0.42
    Grpc
    -0.41
    ,
    -0.40
     also
    -0.39
    کنش
    -0.37
     ראש
    -0.37
    POSITIVE LOGITS
     AssemblyCompany
    0.91
    __":
    0.84
    __':
    0.81
    KommentareTeilen
    0.77
    BeginInit
    0.75
    AnchorStyles
    0.73
     AssemblyCulture
    0.71
    CloseOperation
    0.71
     Wikimedijinoj
    0.70
    ₂+
    0.70
    Activations Density 0.939%

    No Known Activations