© 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. 23816
    Prev
    Next
    INDEX
    Explanations

    sentences or phrases that contain the word "on" or variations thereof

    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
     گوید
    -0.52
    d
    -0.49
    Eloquent
    -0.48
     Isa
    -0.47
     ľah
    -0.47
    D
    -0.45
     }?>
    -0.45
     NgModule
    -0.44
    ·
    -0.44
    وج
    -0.44
    POSITIVE LOGITS
     Roskov
    1.05
    abestanden
    1.03
    帖最后由
    0.95
     snippetHide
    0.94
    IVEREF
    0.92
     समीक्षाओं
    0.87
    Personendaten
    0.83
     disambiguazione
    0.82
    MigrationBuilder
    0.82
    findpost
    0.81
    Activations Density 0.001%

    No Known Activations