© 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. 3599
    Prev
    Next
    INDEX
    Explanations

    never

    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
    soon
    -0.60
     soon
    -0.57
     frattempo
    -0.55
    Soon
    -0.54
     []);
    -0.54
     Soon
    -0.49
     sementara
    -0.49
    <bos>
    -0.48
     sebelumnya
    -0.47
     SOON
    -0.46
    POSITIVE LOGITS
     gyhoeddwyd
    0.57
    ocere
    0.57
     FetchType
    0.57
    ighorn
    0.56
     BitmapFactory
    0.56
    ascin
    0.54
     QtCore
    0.54
     undeniable
    0.53
    ankt
    0.53
    QtCore
    0.53
    Activations Density 0.016%

    No Known Activations