© 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. 4-CLT-HP
    7. 2523
    Prev
    Next
    INDEX
    Explanations

    code snippets and "so"

    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
    LookAnd
    -0.63
    HideFlags
    -0.57
    ostante
    -0.57
    Затем
    -0.57
    tagHelperRunner
    -0.56
     then
    -0.56
    Then
    -0.54
    SuccessListener
    -0.54
     vervolgens
    -0.52
     oprot
    -0.52
    POSITIVE LOGITS
    astie
    0.48
     estúdio
    0.46
    ocyan
    0.46
     defaultstate
    0.44
     principio
    0.42
    đe
    0.42
     utafitiHapana
    0.42
    SetBool
    0.40
     praça
    0.40
    ho
    0.40
    Activations Density 0.002%

    No Known Activations