© 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. 3-RES-MATRYOSHKA-DC
    7. 1642
    Prev
    Next
    INDEX
    Explanations

    the word "post" followed by a hyphen or another word

    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
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyVersion
    -0.80
    DockStyle
    -0.79
    __(/*!
    -0.76
     оригіналу
    -0.72
     localObject
    -0.68
     Numerade
    -0.65
     PropTypes
    -0.64
    WebControls
    -0.63
     дописавши
    -0.63
    rrggbb
    -0.62
    POSITIVE LOGITS
     post
    3.61
     Post
    3.44
    post
    3.36
    Post
    3.34
     POST
    3.03
     posts
    2.94
    POST
    2.83
     Posts
    2.80
    posts
    2.59
    Posts
    2.50
    Activations Density 0.231%

    No Known Activations