© 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. 5-CLT-HP
    7. 2280
    Prev
    Next
    INDEX
    Explanations

    informational text/reports

    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
     AttributeSet
    -0.58
    Vidite
    -0.57
    fony
    -0.57
     alu
    -0.51
    aturas
    -0.50
    <bos>
    -0.49
    avigation
    -0.49
     Utopia
    -0.49
     Vines
    -0.48
     spots
    -0.47
    POSITIVE LOGITS
    المناصب
    0.72
    rungsseite
    0.60
    ⓧ
    0.57
     värld
    0.56
     färg
    0.55
    EndInit
    0.54
     nakalista
    0.53
    DockStyle
    0.53
     TextAppearance
    0.53
    ored
    0.50
    Activations Density 0.044%

    No Known Activations