© 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. 5627
    Prev
    Next
    INDEX
    Explanations

    mechanical

    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
    Revenir
    -0.69
    AccessorTable
    -0.54
    BUN
    -0.50
    /*
    -0.49
     utafiti
    -0.49
     metav
    -0.49
     kicking
    -0.47
    PROLOG
    -0.47
     foundation
    -0.46
    fvar
    -0.46
    POSITIVE LOGITS
     tartalomajánló
    0.55
    Gweler
    0.52
     Италијани
    0.51
    itoba
    0.51
     /\.
    0.51
     مرئيه
    0.50
    LabelTagHelper
    0.50
     Walkover
    0.49
     виправивши
    0.49
     getRule
    0.49
    Activations Density 0.001%

    No Known Activations