© 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. 10190
    Prev
    Next
    INDEX
    Explanations

    references to users and their interactions or edits within a system

    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
     <<<<<<<<<<<<<<
    -0.77
    >--}}
    -0.60
    <<<<<<<<
    -0.60
     informática
    -0.57
    #+#
    -0.56
    Naissance
    -0.55
    UVWXYZ
    -0.54
    .*")]
    -0.54
     FetchType
    -0.54
    éndolo
    -0.54
    POSITIVE LOGITS
    InitVars
    0.63
    InjectAttribute
    0.54
    AutoScaleMode
    0.52
     BoxFit
    0.47
     coef
    0.46
    AutoScale
    0.45
    TestBed
    0.45
    Panamoan
    0.44
    DockStyle
    0.44
    nocześnie
    0.43
    Activations Density 0.129%

    No Known Activations