© 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. 716
    Prev
    Next
    INDEX
    Explanations

    the word "clear" or its variants, often in financial or environmental contexts

    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
    Bibliograf
    -0.72
    yntaxException
    -0.69
    FTFY
    -0.69
    DrawerToggle
    -0.65
     parlent
    -0.63
    #+#
    -0.63
    Cordialement
    -0.63
    BindingSource
    -0.60
    bibliography
    -0.59
    RequiresApi
    -0.58
    POSITIVE LOGITS
     clear
    1.63
    Clear
    1.60
     Clear
    1.59
     CLEAR
    1.58
    clear
    1.44
     clears
    1.40
    CLEAR
    1.40
     Clears
    1.35
     cleared
    1.21
     clearer
    1.16
    Activations Density 0.244%

    No Known Activations