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. 74601
    Prev
    Next
    INDEX
    Explanations

    Code and names

    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
     صوتيه
    -0.62
    setVerticalGroup
    -0.57
    ContentAlignment
    -0.46
     restitu
    -0.46
     (°
    -0.45
    Tē
    -0.44
    ⓧ
    -0.44
     responsibility
    -0.44
    !*\
    -0.43
     aho
    -0.43
    POSITIVE LOGITS
     OnInit
    0.64
    发表于
    0.64
    RenderAtEndOf
    0.63
    })).
    0.56
     TestBed
    0.56
    %");
    0.55
    mika
    0.55
    ismet
    0.54
    CopyWith
    0.52
    galus
    0.52
    Activations Density 0.000%

    No Known Activations