© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 93503
    Prev
    Next
    INDEX
    Explanations

    "-ing" suffix words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :
    -0.79
    StoryboardSegue
    -0.67
    Rohy
    -0.64
    withIdentifier
    -0.63
    хьтан
    -0.63
    _:
    -0.63
    :
    -0.63
     resourceCulture
    -0.62
    __:
    -0.59
    posedge
    -0.59
    POSITIVE LOGITS
    Rüyada
    0.53
    iblichen
    0.50
     Audiodateien
    0.48
    xicity
    0.46
    脚注の使い方
    0.46
    lsp
    0.45
     onlyOwner
    0.45
    apult
    0.44
     transferable
    0.44
     ziua
    0.43
    Activations Density 0.001%

    No Known Activations