© 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. 42035
    Prev
    Next
    INDEX
    Explanations

    Red Hat, fever, Hats

    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
    -0.50
     care
    -0.48
     "
    -0.47
     
    -0.46
    -
    -0.46
    by
    -0.45
    masını
    -0.45
    ">//
    -0.44
     com
    -0.44
    marle
    -0.44
    POSITIVE LOGITS
     Monfieur
    0.87
     iſt
    0.86
     Majefty
    0.84
    KommentareTeilen
    0.81
     quæ
    0.79
     BoxDecoration
    0.79
    tagHelperRunner
    0.77
     Efq
    0.77
     Administrativna
    0.76
     Houſe
    0.75
    Activations Density 0.027%

    No Known Activations