Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 73903
    Prev
    Next
    INDEX
    Explanations

    Finance and proposals

    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
    اریخ
    -0.64
     الحره
    -0.62
    énario
    -0.62
    ModelForm
    -0.61
    ollectionView
    -0.60
     المعيارى
    -0.60
    cault
    -0.60
     TestBed
    -0.60
    xffffff
    -0.59
     Reverso
    -0.58
    POSITIVE LOGITS
    riche
    0.43
    ">//
    0.42
    _));
    0.41
    bjs
    0.40
     saites
    0.39
    roasted
    0.38
    bre
    0.37
    bal
    0.36
    ']/
    0.36
    hor
    0.35
    Activations Density 0.000%

    No Known Activations