© 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. 3348
    Prev
    Next
    INDEX
    Explanations

    Scientific/Technical documents

    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
    findpost
    -0.64
     Forumite
    -0.57
     crdi
    -0.56
     محفوظة
    -0.50
     Hopf
    -0.50
    さぎ
    -0.49
     bezeichneter
    -0.48
    rungsseite
    -0.47
    〢
    -0.46
     suv
    -0.46
    POSITIVE LOGITS
     was
    0.60
    autorest
    0.57
     parts
    0.54
    igshid
    0.54
     مشين
    0.52
    PutMapping
    0.52
     Was
    0.52
    ClientRect
    0.51
     Prieto
    0.50
     instance
    0.49
    Activations Density 0.001%

    No Known Activations