© 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. 93246
    Prev
    Next
    INDEX
    Explanations

    area

    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
    OrFail
    -0.62
     esternos
    -0.62
     chi̍t
    -0.57
    aperto
    -0.55
     bağlantılar
    -0.54
     widerrufen
    -0.52
     Vrbo
    -0.51
     tepi
    -0.51
     Blaine
    -0.51
    Libre
    -0.51
    POSITIVE LOGITS
    ]")]
    0.59
    ArgsConstructor
    0.56
     Exacts
    0.55
     szóci
    0.52
     transfieras
    0.51
    BeginContext
    0.50
    loride
    0.49
    setVerticalGroup
    0.49
    FieldBuilder
    0.49
     apprehend
    0.48
    Activations Density 0.005%

    No Known Activations