© 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. 92954
    Prev
    Next
    INDEX
    Explanations

    technical descriptions and components

    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
    +#+
    -0.58
     ligiloj
    -0.56
    liest
    -0.54
    awtextra
    -0.51
     invokingState
    -0.50
    IntoConstraints
    -0.49
    XtraReports
    -0.48
    ]='\
    -0.48
    moveToFirst
    -0.48
     Geraadpleegd
    -0.47
    POSITIVE LOGITS
     '\\;'
    0.69
    basicConfig
    0.65
    mêmes
    0.54
    konomi
    0.52
     createTime
    0.51
     Allí
    0.51
    mtrl
    0.50
     Rücken
    0.50
    enzial
    0.50
     Depends
    0.49
    Activations Density 0.006%

    No Known Activations