© 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. 18-RES-MATRYOSHKA-DC
    7. 1182
    Prev
    Next
    INDEX
    Explanations

    occurrences of the digit 0

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.18.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.18.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
     Sommers
    -0.71
    classmethod
    -0.65
    iedler
    -0.63
    -0.59
     Darmstadt
    -0.59
    était
    -0.58
    dehydes
    -0.57
     Nuss
    -0.56
    らの
    -0.55
    Rafael
    -0.54
    POSITIVE LOGITS
    awtextra
    0.97
     defaultstate
    0.92
    RegressionTest
    0.84
     Kild
    0.84
    AddTagHelper
    0.82
    jmniej
    0.82
    AndEndTag
    0.82
    Hentet
    0.82
    0
    0.81
    vician
    0.81
    Activations Density 1.403%

    No Known Activations