© 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. 20-CLT-HP
    7. 76681
    Prev
    Next
    INDEX
    Explanations

    code or unusual text

    np_max-act-logits · 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
    stdc
    -0.80
    ArrowToggle
    -0.80
     juſ
    -0.76
     normaux
    -0.76
     gjø
    -0.75
     présidenti
    -0.74
     mouths
    -0.74
     brancas
    -0.74
    StoryboardSegue
    -0.72
     صوتيه
    -0.72
    POSITIVE LOGITS
     nog
    0.41
     '\\;'
    0.40
    uter
    0.38
    fjspx
    0.32
     ticker
    0.32
    opes
    0.32
     Ari
    0.31
     Coupons
    0.31
     master
    0.31
    unmodifiable
    0.31
    Activations Density 0.000%

    No Known Activations