© 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
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 74695
    Prev
    Next
    INDEX
    Explanations

    Code/technical text

    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
    原始内容存档于
    -0.52
    المناصب
    -0.52
    JoinColumn
    -0.49
    LayoutConstraint
    -0.47
     gewähr
    -0.46
     deck
    -0.45
    kra
    -0.44
    unkt
    -0.44
    دار
    -0.43
    ](#
    -0.43
    POSITIVE LOGITS
    MemoryWarning
    0.89
    BagConstraints
    0.67
     Wikimédia
    0.66
    ⓧ
    0.60
    PYX
    0.60
    ParallelGroup
    0.59
    expandindo
    0.59
     Biôgrafia
    0.59
     мәкалә
    0.58
    SequentialGroup
    0.58
    Activations Density 0.000%

    No Known Activations