© 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. 11945
    Prev
    Next
    INDEX
    Explanations

    the word "apparent" and its various forms

    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
     GenerationType
    -0.96
     فريبيس
    -0.84
     finnas
    -0.79
    fromLTRB
    -0.75
    PYX
    -0.75
     الحره
    -0.69
    timbangkan
    -0.68
    ớt
    -0.65
     Soko
    -0.65
     ThemeData
    -0.63
    POSITIVE LOGITS
    AppComponent
    0.75
     Flä
    0.73
     doInBackground
    0.72
     Apparent
    0.72
     Vallarta
    0.69
     Peabody
    0.66
    prnt
    0.66
    swick
    0.65
     Canopy
    0.65
     Gallimard
    0.65
    Activations Density 0.009%

    No Known Activations