© 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. 1-CLT-HP
    7. 14909
    Prev
    Next
    INDEX
    Explanations

    At As

    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
     the
    -1.38
     a
    -1.27
     an
    -1.11
     one
    -0.85
     its
    -0.82
     this
    -0.81
     their
    -0.79
     those
    -0.78
     any
    -0.77
     some
    -0.76
    POSITIVE LOGITS
     poussière
    0.69
     revés
    0.65
    stdc
    0.56
     通販
    0.55
     lisäksi
    0.51
     stället
    0.48
     olvido
    0.48
     poignée
    0.47
     mesmos
    0.47
     cérami
    0.45
    Activations Density 0.191%

    No Known Activations