© 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. 0-CLT-HP
    7. 42668
    Prev
    Next
    INDEX
    Explanations

    Math problems

    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
    <bos>
    -1.53
     AssemblyCulture
    -0.91
     myſelf
    -0.86
     ſtate
    -0.80
     cauſe
    -0.79
     raiſ
    -0.78
     pleaſure
    -0.77
     Monfieur
    -0.77
    OGND
    -0.75
     Cæsar
    -0.75
    POSITIVE LOGITS
     Amp
    0.50
     Else
    0.47
     semp
    0.46
     fram
    0.43
     Add
    0.42
    "]();
    0.42
    zij
    0.42
     éven
    0.40
     Put
    0.40
    ")}
    0.40
    Activations Density 0.146%

    No Known Activations