© 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. 94402
    Prev
    Next
    INDEX
    Explanations

    and

    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
     noDo
    -0.45
    <bos>
    -0.45
    InstanceState
    -0.41
    enderror
    -0.40
    municipi
    -0.40
    ="#
    -0.39
     Populate
    -0.38
    ksom
    -0.38
     Савезне
    -0.37
    cyclic
    -0.37
    POSITIVE LOGITS
    awtextra
    0.75
     CreateTagHelper
    0.74
    MessageOf
    0.73
     >=",
    0.70
    AndEndTag
    0.64
    ArgsConstructor
    0.59
     Италијани
    0.59
     Վերցված
    0.57
    Hozzáférés
    0.57
    SourceChecksum
    0.57
    Activations Density 0.003%

    No Known Activations