© 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. 5-CLT-HP
    7. 92753
    Prev
    Next
    INDEX
    Explanations

    machine learning, AI

    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
    ':[
    -0.45
    alanx
    -0.41
    oa̍t
    -0.41
    𝓋
    -0.40
    hood
    -0.40
    ngdoc
    -0.38
    HOOD
    -0.38
    Rohy
    -0.37
    neté
    -0.37
    rix
    -0.37
    POSITIVE LOGITS
    OGND
    0.67
     Diſ
    0.65
     belongs
    0.65
     itſelf
    0.64
     learns
    0.61
     garcía
    0.61
    RefNanny
    0.60
     inoxydable
    0.60
    rungsseite
    0.60
     ſhould
    0.60
    Activations Density 0.000%

    No Known Activations