© 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. 5-CLT-HP
    7. 95053
    Prev
    Next
    INDEX
    Explanations

    which

    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
     to
    -0.71
    oredCriteria
    -0.56
    <bos>
    -0.51
    every
    -0.48
     every
    -0.45
    fatti
    -0.45
     todas
    -0.44
    ibrill
    -0.43
     even
    -0.43
    even
    -0.42
    POSITIVE LOGITS
     kasarigan
    0.78
     they
    0.77
     }}"></
    0.74
    SequentialGroup
    0.73
    ChildScrollView
    0.73
     AttributeSet
    0.71
    HasForeignKey
    0.68
     سكانية
    0.68
    ęku
    0.67
    __(/*!
    0.67
    Activations Density 0.006%

    No Known Activations