© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 45700
    Prev
    Next
    INDEX
    Explanations

    oid/roids

    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
    getSub
    -0.56
     ruban
    -0.52
     résister
    -0.51
     nærm
    -0.47
    rdı
    -0.47
     independientes
    -0.46
    űr
    -0.46
     quæ
    -0.46
     alvor
    -0.45
     colectiva
    -0.45
    POSITIVE LOGITS
    AndEndTag
    0.94
     oprot
    0.81
     صوتيه
    0.70
     otomatig
    0.69
     الدولى
    0.68
    InitVars
    0.67
    ChildScrollView
    0.66
    RTEX
    0.65
    PRWEB
    0.63
    __':
    0.62
    Activations Density 0.076%

    No Known Activations