© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 94866
    Prev
    Next
    INDEX
    Explanations

    fun

    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
    quilla
    -0.45
     related
    -0.45
     my
    -0.45
     basic
    -0.45
     base
    -0.45
    3
    -0.43
    4
    -0.43
    inin
    -0.41
     mon
    -0.41
     leg
    -0.41
    POSITIVE LOGITS
    脚注の使い方
    0.89
    ]")]
    0.81
    TemporalType
    0.76
    ">//
    0.72
    =$?
    0.71
    RenderAtEndOf
    0.70
    ագրություններ
    0.69
    SerializedSize
    0.69
    enterOuterAlt
    0.66
     Efq
    0.66
    Activations Density 0.001%

    No Known Activations