© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 96227
    Prev
    Next
    INDEX
    Explanations

    ,

    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
    ReusableCell
    -0.56
    __*/
    -0.56
     localObject
    -0.54
     ujednoznacz
    -0.52
     Negroes
    -0.52
    MemoryWarning
    -0.51
    +#+#
    -0.51
     JpaRepository
    -0.49
    sizeCache
    -0.49
     absorbing
    -0.48
    POSITIVE LOGITS
    loài
    0.59
    ::*;
    0.56
    kip
    0.54
    kään
    0.54
     Need
    0.53
     Increase
    0.52
     person
    0.52
    
    0.51
    denes
    0.50
    geleitet
    0.50
    Activations Density 0.005%

    No Known Activations