© 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. 5-CLT-HP
    7. 5734
    Prev
    Next
    INDEX
    Explanations

    Put

    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
    Jeografia
    -0.64
    (""),
    -0.64
    #
    -0.58
     kasarigan
    -0.57
    (''),
    -0.54
    ,
    -0.53
    %"),
    -0.53
     cdti
    -0.51
     OFDb
    -0.51
    hatenablog
    -0.50
    POSITIVE LOGITS
    .
    1.24
     conçus
    0.68
     køb
    0.63
     concernés
    0.60
     diseñados
    0.60
     clínicos
    0.59
     destinés
    0.58
     formales
    0.58
     específicos
    0.58
     diseñada
    0.56
    Activations Density 0.000%

    No Known Activations