© 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. 97625
    Prev
    Next
    INDEX
    Explanations

    trying

    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
    Chooser
    -0.53
    CMA
    -0.52
     fusca
    -0.52
     options
    -0.51
     littéraire
    -0.50
     löyty
    -0.49
     CMA
    -0.48
     be
    -0.48
    Cd
    -0.47
     ganda
    -0.46
    POSITIVE LOGITS
    Personendaten
    0.81
    awtextra
    0.73
    InitStruct
    0.72
    脚注の使い方
    0.68
    __":
    0.68
    AddTagHelper
    0.65
     doInBackground
    0.65
    erover
    0.62
     localVar
    0.62
    providedIn
    0.59
    Activations Density 0.003%

    No Known Activations