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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 97094
    Prev
    Next
    INDEX
    Explanations

    als

    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
     greatly
    -1.06
     considerably
    -1.05
     immensely
    -1.04
     tremendously
    -1.03
     InputDecoration
    -0.98
     enormously
    -0.98
     significantly
    -0.94
     much
    -0.93
     substantially
    -0.92
     hugely
    -0.90
    POSITIVE LOGITS
    saraba
    0.46
    ,
    0.45
    +(\
    0.43
    considering
    0.42
    :
    0.42
    rededor
    0.40
    ​​​
    0.40
    年前
    0.40
    Later
    0.38
    activating
    0.38
    Activations Density 0.008%

    No Known Activations