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. 73602
    Prev
    Next
    INDEX
    Explanations

    Technical language

    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
    ArrowToggle
    -0.98
    MigrationBuilder
    -0.79
    Хро
    -0.71
    Performed
    -0.68
    Worked
    -0.66
    IndentedString
    -0.66
     Performed
    -0.65
    performed
    -0.65
    AndEndTag
    -0.64
    sidemargin
    -0.64
    POSITIVE LOGITS
     happens
    0.55
    len
    0.53
     ends
    0.46
    ends
    0.41
     becomes
    0.40
     do
    0.40
    lir
    0.40
    lle
    0.39
    lt
    0.37
     carrés
    0.37
    Activations Density 0.000%

    No Known Activations