© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 40630
    Prev
    Next
    INDEX
    Explanations

    temp

    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
     temp
    -1.20
    Temp
    -1.16
    temp
    -1.12
     Temp
    -1.11
    tmp
    -0.88
     TEMP
    -0.86
     tmp
    -0.84
    TEMP
    -0.83
     beast
    -0.81
    Tmp
    -0.74
    POSITIVE LOGITS
    setVerticalGroup
    0.91
     дописавши
    0.73
    Referencie
    0.68
    Personendaten
    0.66
     ModelExpression
    0.66
    makeConstraints
    0.66
    wikidata
    0.65
     springfox
    0.64
    EndProject
    0.62
     CanadaChoose
    0.62
    Activations Density 1.755%

    No Known Activations