© 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. 42797
    Prev
    Next
    INDEX
    Explanations

    subjective evaluations

    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>
    -0.66
    ities
    -0.50
    s
    -0.46
     prices
    -0.43
     nop
    -0.42
     directions
    -0.41
     participated
    -0.40
     portions
    -0.40
     access
    -0.40
    izes
    -0.40
    POSITIVE LOGITS
    ReusableCell
    0.81
    protoimpl
    0.77
     resourceCulture
    0.77
    солю
    0.75
    XmlAccessorType
    0.75
    tvguidetime
    0.74
    setViewportView
    0.74
     MainAxisSize
    0.74
    ngdoc
    0.73
    complexContent
    0.73
    Activations Density 0.077%

    No Known Activations