© 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. 0-CLT-HP
    7. 97436
    Prev
    Next
    INDEX
    Explanations

    question

    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
     their
    -0.58
     it
    -0.56
    äsident
    -0.56
     Their
    -0.52
    loro
    -0.52
     they
    -0.51
     he
    -0.49
     you
    -0.48
     którzy
    -0.47
    ModelForm
    -0.46
    POSITIVE LOGITS
     pleaſure
    0.94
     فريبيس
    0.85
     itſelf
    0.84
     myſelf
    0.82
     purpoſe
    0.82
     Monfieur
    0.81
     juſ
    0.80
     defences
    0.80
     HasFactory
    0.79
     Италијани
    0.78
    Activations Density 0.172%

    No Known Activations