© 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. 5399
    Prev
    Next
    INDEX
    Explanations

    technical concepts

    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
    runApp
    -0.71
    }\]
    -0.68
     ſtand
    -0.67
    __*/
    -0.66
     houſe
    -0.65
     reaſon
    -0.65
     ſmall
    -0.63
     CanadaChoose
    -0.63
     مرئيه
    -0.62
     ſhould
    -0.61
    POSITIVE LOGITS
     and
    0.51
    yntaxException
    0.45
     sucedido
    0.44
    EnableWeb
    0.43
    ,
    0.42
     characteristics
    0.41
    Referències
    0.40
     affecting
    0.40
    Portale
    0.40
    yup
    0.40
    Activations Density 0.029%

    No Known Activations