© 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. 0-CLT-HP
    7. 41608
    Prev
    Next
    INDEX
    Explanations

    Essentially/stems

    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
     stems
    -1.02
    stem
    -0.80
     stemmed
    -0.79
     activation
    -0.64
     stemming
    -0.62
    はじめに
    -0.59
     activations
    -0.59
     Activation
    -0.58
     Basically
    -0.55
     Outre
    -0.53
    POSITIVE LOGITS
    +#+
    0.67
    ConstraintMaker
    0.60
    Hozzáférés
    0.58
    photobucket
    0.56
    #+#
    0.55
     سكانية
    0.53
    NameInMap
    0.53
    ized
    0.52
    WritableDatabase
    0.52
    resizingMask
    0.52
    Activations Density 0.118%

    No Known Activations