© 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. 0-CLT-HP
    7. 42382
    Prev
    Next
    INDEX
    Explanations

    cryptocurrency

    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
    evil
    -0.78
     Lawyer
    -0.62
     evil
    -0.61
    eer
    -0.61
     crypto
    -0.60
    embedded
    -0.60
    YourGuide
    -0.60
     noDo
    -0.60
     bitcoin
    -0.59
    bitcoin
    -0.59
    POSITIVE LOGITS
    nya
    0.74
    ness
    0.69
    cinnati
    0.60
    IntoConstraints
    0.57
    ization
    0.56
    ty
    0.54
    isation
    0.53
    ly
    0.52
    脚注の使い方
    0.52
    stdc
    0.51
    Activations Density 0.105%

    No Known Activations