© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 77021
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    CodedInputStream
    -0.51
    <
    -0.42
    uncher
    -0.41
    setVerticalGroup
    -0.40
     вдох
    -0.37
    REAS
    -0.36
     Landes
    -0.36
     mema
    -0.36
     T
    -0.36
    cshtml
    -0.35
    POSITIVE LOGITS
    ########.
    0.71
    webElementXpaths
    0.69
    évaluateur
    0.68
     Baillargeon
    0.68
    oa̍t
    0.67
    ьаж
    0.67
     CascadeType
    0.66
     صوتيه
    0.65
     Exacts
    0.65
    clusal
    0.64
    Activations Density 0.002%

    No Known Activations