© 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. 5-CLT-HP
    7. 3734
    Prev
    Next
    INDEX
    Explanations

    common words

    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
    Applet
    -0.59
     Statistical
    -0.57
     fær
    -0.55
    thâu
    -0.55
    XmlAccessType
    -0.55
    Propor
    -0.54
     averages
    -0.54
     outnumbered
    -0.54
     Propor
    -0.53
    MENAFN
    -0.53
    POSITIVE LOGITS
    ImageField
    0.56
     ddelweddau
    0.50
    Kjelder
    0.46
    Referințe
    0.45
    ="?
    0.44
    ories
    0.43
    Carriera
    0.42
    ]-->
    0.41
    <bos>
    0.40
    AutoField
    0.40
    Activations Density 0.002%

    No Known Activations