© 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. 97261
    Prev
    Next
    INDEX
    Explanations

    iko

    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
    bootstrapcdn
    -0.82
     الرياضيه
    -0.77
    WebVitals
    -0.65
     useAppContext
    -0.65
    ArgsConstructor
    -0.65
    tagHelperRunner
    -0.65
     Roskov
    -0.64
    iko
    -0.64
     Theſe
    -0.63
     molecule
    -0.62
    POSITIVE LOGITS
    as
    0.58
    ix
    0.55
    iseksi
    0.55
    ixer
    0.52
    equ
    0.52
    Blas
    0.50
     monstruos
    0.49
    eros
    0.48
    </thead>
    0.48
    bladder
    0.48
    Activations Density 0.941%

    No Known Activations