© 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. 42833
    Prev
    Next
    INDEX
    Explanations

    actions

    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
     autorytatywna
    -0.67
    <bos>
    -0.66
     betweenstory
    -0.60
     P
    -0.56
     باخ
    -0.54
     T
    -0.51
     C
    -0.51
     ویکی‌پدی
    -0.50
     La
    -0.48
     it
    -0.47
    POSITIVE LOGITS
     OnInit
    0.81
     HasFactory
    0.78
     فريبيس
    0.73
    RUnlock
    0.71
     <<<<<<<<<<<<<<
    0.70
    ellees
    0.69
     Inflate
    0.69
     Zorg
    0.69
     FMI
    0.68
    tilhe
    0.68
    Activations Density 0.079%

    No Known Activations